Skip to content

aiskillstore/marketplace / skills/aaron-he-zhu/email-quality-auditor

email-quality-auditor

Verified

Use when the user asks to "audit an email program" or "is this campaign safe to send"; runs a typed 20-item SEND profile with authentication, consent, opt-out, and claim veto checks on own evidence. Not for building deliverability setup — use deliverability-qa; not for designing lifecycle flows — use email-sequence-designer. 邮件质量审计/EQS评分/发送前放行

FileKindSize
SKILL.mdskill md8.0 KB
references/auditor-runtime.mdmarkdown8.1 KB
skill-report.jsonconfig38.2 KB

skill-report.json

View on GitHub
{
  "schema_version": "2.0",
  "meta": {
    "generated_at": "2026-07-26T10:14:54.622Z",
    "slug": "aaron-he-zhu-email-quality-auditor",
    "source_url": "https://github.com/aaron-he-zhu/aaron-marketing-skills/tree/main/email/deliver/email-quality-auditor",
    "source_ref": "main",
    "model": "claude",
    "analysis_version": "3.0.0",
    "source_type": "community",
    "content_hash": "568baed61875730d5fe235163ed43864e103b94d63030211b9112363ad8a1f2d",
    "tree_hash": "0cc51e76ae8e55c64d63dc65db74fe93065bea75cc981dcf607aa71248fbebea",
    "provenance": {
      "model_effective": "claude",
      "fallback_chain": [
        {
          "agent": "codex",
          "outcome": "failed",
          "error": "2026-07-26T10:14:54.717201Z ERROR codex_models_manager::manager: failed to refresh available models: Missing environment variable: `HELM_API_KEY`.\n2026-07-26T10:14:54.752704Z ERROR codex_models_manage…"
        },
        {
          "agent": "claude",
          "outcome": "success"
        }
      ],
      "analysis_version": "3.0.0"
    },
    "upstream_version_raw": "19.0.0",
    "upstream_version_normalized": "19.0.0",
    "upstream_version_source": "metadata.version",
    "upstream_version_status": "not_bumped",
    "upstream_commit_sha": "49c026d9d90630ed187fbce5c7f7f84ff4710d85"
  },
  "skill": {
    "name": "email-quality-auditor",
    "description": "Audits an email program or planned send against a 20-item SEND profile. It checks evidence for authentication, consent, opt-out handling, claims, and measurement before release.",
    "summary": "Assess email readiness with evidence-based SEND gates.",
    "icon": "📦",
    "version": "19.0.0",
    "author": "aaron-he-zhu",
    "license": "Apache-2.0",
    "tags": [
      "email audit",
      "deliverability",
      "consent",
      "campaign QA",
      "SEND scoring"
    ],
    "supported_tools": [
      "claude",
      "codex",
      "claude-code"
    ],
    "risk_factors": [
      "external_commands",
      "network",
      "filesystem"
    ],
    "category": "communication"
  },
  "security_audit": {
    "risk_level": "safe",
    "is_blocked": false,
    "safe_to_publish": true,
    "analysis_status": "ok",
    "summary": "All 34 static findings are false positives caused by Markdown backticks, fixed local reference links, and homepage metadata. The reviewed instructions emphasize evidence-based email audits, prohibit autonomous sending and provider changes, and require explicit authorization before persistence. No prompt injection, exfiltration intent, or user-controlled command or path execution was found.",
    "remediation": [
      {
        "issue": "Automated scanners interpret Markdown backticks as shell execution.",
        "suggestion": "Use fenced prose or clearly label inline tokens as documentation examples where practical.",
        "severity": "low"
      },
      {
        "issue": "Package-relative links trigger path traversal detectors.",
        "suggestion": "Prefer skill-host reference resolution or document that these links are fixed package references.",
        "severity": "low"
      },
      {
        "issue": "The setup section includes a shell-style repository-root expression.",
        "suggestion": "Replace it with host-provided root resolution when available, or state that the command has fixed arguments and no user input.",
        "severity": "low"
      }
    ],
    "risk_factor_evidence": [
      {
        "factor": "external_commands",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 30,
            "line_end": 33
          },
          {
            "file": "SKILL.md",
            "line_start": 33,
            "line_end": 39
          },
          {
            "file": "SKILL.md",
            "line_start": 39,
            "line_end": 39
          },
          {
            "file": "SKILL.md",
            "line_start": 57,
            "line_end": 57
          },
          {
            "file": "SKILL.md",
            "line_start": 59,
            "line_end": 64
          },
          {
            "file": "SKILL.md",
            "line_start": 64,
            "line_end": 65
          },
          {
            "file": "SKILL.md",
            "line_start": 65,
            "line_end": 65
          },
          {
            "file": "SKILL.md",
            "line_start": 67,
            "line_end": 68
          },
          {
            "file": "SKILL.md",
            "line_start": 68,
            "line_end": 69
          },
          {
            "file": "SKILL.md",
            "line_start": 69,
            "line_end": 70
          },
          {
            "file": "SKILL.md",
            "line_start": 70,
            "line_end": 73
          },
          {
            "file": "SKILL.md",
            "line_start": 73,
            "line_end": 77
          },
          {
            "file": "SKILL.md",
            "line_start": 77,
            "line_end": 78
          },
          {
            "file": "SKILL.md",
            "line_start": 78,
            "line_end": 79
          },
          {
            "file": "SKILL.md",
            "line_start": 79,
            "line_end": 80
          },
          {
            "file": "SKILL.md",
            "line_start": 80,
            "line_end": 84
          },
          {
            "file": "SKILL.md",
            "line_start": 84,
            "line_end": 92
          },
          {
            "file": "SKILL.md",
            "line_start": 92,
            "line_end": 96
          },
          {
            "file": "SKILL.md",
            "line_start": 96,
            "line_end": 96
          },
          {
            "file": "SKILL.md",
            "line_start": 110,
            "line_end": 110
          },
          {
            "file": "SKILL.md",
            "line_start": 57,
            "line_end": 57
          },
          {
            "file": "SKILL.md",
            "line_start": 57,
            "line_end": 57
          }
        ]
      },
      {
        "factor": "network",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 10,
            "line_end": 10
          },
          {
            "file": "SKILL.md",
            "line_start": 15,
            "line_end": 15
          }
        ]
      },
      {
        "factor": "filesystem",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 57,
            "line_end": 57
          },
          {
            "file": "SKILL.md",
            "line_start": 114,
            "line_end": 114
          },
          {
            "file": "SKILL.md",
            "line_start": 115,
            "line_end": 115
          },
          {
            "file": "SKILL.md",
            "line_start": 116,
            "line_end": 116
          },
          {
            "file": "SKILL.md",
            "line_start": 117,
            "line_end": 117
          },
          {
            "file": "SKILL.md",
            "line_start": 121,
            "line_end": 121
          },
          {
            "file": "SKILL.md",
            "line_start": 122,
            "line_end": 122
          },
          {
            "file": "SKILL.md",
            "line_start": 123,
            "line_end": 123
          },
          {
            "file": "SKILL.md",
            "line_start": 124,
            "line_end": 124
          },
          {
            "file": "SKILL.md",
            "line_start": 57,
            "line_end": 57
          }
        ]
      }
    ],
    "static_findings": [
      {
        "id": "external_commands:SKILL.md:30:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 30,
        "line_end": 33,
        "snippet": "```text"
      },
      {
        "id": "external_commands:SKILL.md:33:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 33,
        "line_end": 39,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:39:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 39,
        "line_end": 39,
        "snippet": "Use `deliverability-qa` to repair authentication, `consent-registry` for lawful-basis/suppression fa"
      },
      {
        "id": "external_commands:SKILL.md:57:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 57,
        "line_end": 57,
        "snippet": "Read `../../../references/auditor-runbook.md`, `scoring-semantics.md`, `send-benchmark.md`, and the "
      },
      {
        "id": "external_commands:SKILL.md:59:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 59,
        "line_end": 64,
        "snippet": "Declare profile (`promotional|retention|cold-outbound|newsletter`), target/program, provider, market"
      },
      {
        "id": "external_commands:SKILL.md:64:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 64,
        "line_end": 65,
        "snippet": "2. Score all 20 `S1..D5` criteria. Every observed state requires source/date/type/confidence."
      },
      {
        "id": "external_commands:SKILL.md:65:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 65,
        "line_end": 65,
        "snippet": "3. `E2` is N/A with reason when opens/CTOR are not used. `N3/N5` are conditional by program design. "
      },
      {
        "id": "external_commands:SKILL.md:67:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 67,
        "line_end": 68,
        "snippet": "- `SEND-S1`: required authentication is demonstrably broken/unaligned."
      },
      {
        "id": "external_commands:SKILL.md:68:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 68,
        "line_end": 69,
        "snippet": "- `SEND-S2`: a purchased/scraped/unlawful list is verified; missing provenance is Unknown."
      },
      {
        "id": "external_commands:SKILL.md:69:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 69,
        "line_end": 70,
        "snippet": "- `SEND-N1`: opt-out is broken/absent or a recorded suppression is not honored."
      },
      {
        "id": "external_commands:SKILL.md:70:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 70,
        "line_end": 73,
        "snippet": "- `SEND-D1`: material claim/disclosure/offer term fails approved evidence."
      },
      {
        "id": "external_commands:SKILL.md:73:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 73,
        "line_end": 77,
        "snippet": "For a send-only review without enough program evidence, report the verified red-line checks and exac"
      },
      {
        "id": "external_commands:SKILL.md:77:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 77,
        "line_end": 78,
        "snippet": "- Complete newsletter profile, raw 81, no veto/fail: `DONE/SHIP`, final 81."
      },
      {
        "id": "external_commands:SKILL.md:78:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 78,
        "line_end": 79,
        "snippet": "- Complete promotional profile, raw 76, one verified S1 failure: `DONE_WITH_CONCERNS/FIX`, final 59."
      },
      {
        "id": "external_commands:SKILL.md:79:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 79,
        "line_end": 80,
        "snippet": "- Complete profile, verified S2 and N1 failures: `DONE/BLOCK`, no final score."
      },
      {
        "id": "external_commands:SKILL.md:80:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 80,
        "line_end": 84,
        "snippet": "- Consent provenance absent: S2 Unknown, `NEEDS_INPUT/UNDECIDED`, no score."
      },
      {
        "id": "external_commands:SKILL.md:84:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 84,
        "line_end": 92,
        "snippet": "- DMARC `p=none` with aligned SPF/DKIM and active monitoring is not automatically an S1 failure."
      },
      {
        "id": "external_commands:SKILL.md:92:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 92,
        "line_end": 96,
        "snippet": "Explain channel and recipient risk in plain language. On trace request, qualify `SEND-S1/S2/N1/D1` a"
      },
      {
        "id": "external_commands:SKILL.md:96:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 96,
        "line_end": 96,
        "snippet": "Begin with the auditor-runbook's exact typed conversation header. Never replace `status`, `verdict`,"
      },
      {
        "id": "external_commands:SKILL.md:110:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 110,
        "line_end": 110,
        "snippet": "Persist only after explicit authorization to `memory/audits/email/YYYY-MM-DD-<topic>.md`. Preserve t"
      },
      {
        "id": "external_commands:SKILL.md:57:shell-command-substitution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Shell command substitution",
        "file": "SKILL.md",
        "line_start": 57,
        "line_end": 57,
        "snippet": "Read `../../../references/auditor-runbook.md`, `scoring-semantics.md`, `send-benchmark.md`, and the "
      },
      {
        "id": "external_commands:SKILL.md:57:template-literal-with-command-substitution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Template literal with command substitution",
        "file": "SKILL.md",
        "line_start": 57,
        "line_end": 57,
        "snippet": "Read `../../../references/auditor-runbook.md`, `scoring-semantics.md`, `send-benchmark.md`, and the "
      },
      {
        "id": "network:SKILL.md:10:hardcoded-url",
        "category": "network",
        "severity": "low",
        "pattern": "Hardcoded URL",
        "file": "SKILL.md",
        "line_start": 10,
        "line_end": 10,
        "snippet": "homepage: \"https://github.com/aaron-he-zhu/aaron-marketing-skills\""
      },
      {
        "id": "network:SKILL.md:15:hardcoded-url",
        "category": "network",
        "severity": "low",
        "pattern": "Hardcoded URL",
        "file": "SKILL.md",
        "line_start": 15,
        "line_end": 15,
        "snippet": "metadata: {\"author\": \"aaron-he-zhu\", \"version\": \"19.0.0\", \"discipline\": \"email\", \"phase\": \"deliver\","
      },
      {
        "id": "filesystem:SKILL.md:57:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 57,
        "line_end": 57,
        "snippet": "Read `../../../references/auditor-runbook.md`, `scoring-semantics.md`, `send-benchmark.md`, and the "
      },
      {
        "id": "filesystem:SKILL.md:114:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 114,
        "line_end": 114,
        "snippet": "- [SEND benchmark](../../../references/send-benchmark.md)"
      },
      {
        "id": "filesystem:SKILL.md:115:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 115,
        "line_end": 115,
        "snippet": "- [Measurement protocol](../../../references/measurement-protocol.md)"
      },
      {
        "id": "filesystem:SKILL.md:116:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 116,
        "line_end": 116,
        "snippet": "- [Auditor runbook](../../../references/auditor-runbook.md)"
      },
      {
        "id": "filesystem:SKILL.md:117:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 117,
        "line_end": 117,
        "snippet": "- [Scoring semantics](../../../references/scoring-semantics.md)"
      },
      {
        "id": "filesystem:SKILL.md:121:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 121,
        "line_end": 121,
        "snippet": "- **Authentication/placement:** [deliverability-qa](../../setup/deliverability-qa/SKILL.md)"
      },
      {
        "id": "filesystem:SKILL.md:122:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 122,
        "line_end": 122,
        "snippet": "- **Consent/suppression:** [consent-registry](../../../protocol/consent-registry/SKILL.md)"
      },
      {
        "id": "filesystem:SKILL.md:123:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 123,
        "line_end": 123,
        "snippet": "- **Lifecycle:** [email-sequence-designer](../../nurture/email-sequence-designer/SKILL.md)"
      },
      {
        "id": "filesystem:SKILL.md:124:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 124,
        "line_end": 124,
        "snippet": "- **Experiment:** [send-experiment-designer](../send-experiment-designer/SKILL.md)"
      },
      {
        "id": "filesystem:SKILL.md:57:standard-device-file-access",
        "category": "filesystem",
        "severity": "low",
        "pattern": "Standard device file access",
        "file": "SKILL.md",
        "line_start": 57,
        "line_end": 57,
        "snippet": "Read `../../../references/auditor-runbook.md`, `scoring-semantics.md`, `send-benchmark.md`, and the "
      }
    ],
    "finding_verdicts": [
      {
        "id": "external_commands:SKILL.md:30:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The backticks delimit Markdown examples, identifiers, or file names; they do not invoke Ruby or a shell. No executable command is supplied on this line."
      },
      {
        "id": "external_commands:SKILL.md:33:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The backticks delimit Markdown examples, identifiers, or file names; they do not invoke Ruby or a shell. No executable command is supplied on this line."
      },
      {
        "id": "external_commands:SKILL.md:39:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The backticks delimit Markdown examples, identifiers, or file names; they do not invoke Ruby or a shell. No executable command is supplied on this line."
      },
      {
        "id": "external_commands:SKILL.md:57:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The backticks delimit Markdown examples, identifiers, or file names; they do not invoke Ruby or a shell. No executable command is supplied on this line."
      },
      {
        "id": "external_commands:SKILL.md:59:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The backticks delimit Markdown examples, identifiers, or file names; they do not invoke Ruby or a shell. No executable command is supplied on this line."
      },
      {
        "id": "external_commands:SKILL.md:64:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The backticks delimit Markdown examples, identifiers, or file names; they do not invoke Ruby or a shell. No executable command is supplied on this line."
      },
      {
        "id": "external_commands:SKILL.md:65:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The backticks delimit Markdown examples, identifiers, or file names; they do not invoke Ruby or a shell. No executable command is supplied on this line."
      },
      {
        "id": "external_commands:SKILL.md:67:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The backticks delimit Markdown examples, identifiers, or file names; they do not invoke Ruby or a shell. No executable command is supplied on this line."
      },
      {
        "id": "external_commands:SKILL.md:68:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The backticks delimit Markdown examples, identifiers, or file names; they do not invoke Ruby or a shell. No executable command is supplied on this line."
      },
      {
        "id": "external_commands:SKILL.md:69:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The backticks delimit Markdown examples, identifiers, or file names; they do not invoke Ruby or a shell. No executable command is supplied on this line."
      },
      {
        "id": "external_commands:SKILL.md:70:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The backticks delimit Markdown examples, identifiers, or file names; they do not invoke Ruby or a shell. No executable command is supplied on this line."
      },
      {
        "id": "external_commands:SKILL.md:73:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The backticks delimit Markdown examples, identifiers, or file names; they do not invoke Ruby or a shell. No executable command is supplied on this line."
      },
      {
        "id": "external_commands:SKILL.md:77:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The backticks delimit Markdown examples, identifiers, or file names; they do not invoke Ruby or a shell. No executable command is supplied on this line."
      },
      {
        "id": "external_commands:SKILL.md:78:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The backticks delimit Markdown examples, identifiers, or file names; they do not invoke Ruby or a shell. No executable command is supplied on this line."
      },
      {
        "id": "external_commands:SKILL.md:79:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The backticks delimit Markdown examples, identifiers, or file names; they do not invoke Ruby or a shell. No executable command is supplied on this line."
      },
      {
        "id": "external_commands:SKILL.md:80:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The backticks delimit Markdown examples, identifiers, or file names; they do not invoke Ruby or a shell. No executable command is supplied on this line."
      },
      {
        "id": "external_commands:SKILL.md:84:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The backticks delimit Markdown examples, identifiers, or file names; they do not invoke Ruby or a shell. No executable command is supplied on this line."
      },
      {
        "id": "external_commands:SKILL.md:92:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The backticks delimit Markdown examples, identifiers, or file names; they do not invoke Ruby or a shell. No executable command is supplied on this line."
      },
      {
        "id": "external_commands:SKILL.md:96:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The backticks delimit Markdown examples, identifiers, or file names; they do not invoke Ruby or a shell. No executable command is supplied on this line."
      },
      {
        "id": "external_commands:SKILL.md:110:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The backticks delimit Markdown examples, identifiers, or file names; they do not invoke Ruby or a shell. No executable command is supplied on this line."
      },
      {
        "id": "external_commands:SKILL.md:57:shell-command-substitution",
        "verdict": "false_positive",
        "confidence": 0.9,
        "reason": "The only shell substitution is a fixed git command used to locate the repository root, with no user-controlled argument. It is presented as setup guidance and does not execute arbitrary input."
      },
      {
        "id": "external_commands:SKILL.md:57:template-literal-with-command-substitution",
        "verdict": "false_positive",
        "confidence": 0.95,
        "reason": "The backticks are Markdown formatting around a fixed setup expression, not a dynamically constructed shell command. No untrusted value is interpolated into the expression."
      },
      {
        "id": "network:SKILL.md:10:hardcoded-url",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The URL is homepage metadata only. The skill does not instruct an agent to request it or transmit data to it."
      },
      {
        "id": "network:SKILL.md:15:hardcoded-url",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The URL appears in author metadata. It is not an endpoint used by the skill at runtime."
      },
      {
        "id": "filesystem:SKILL.md:57:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.91,
        "reason": "This is a fixed, package-relative reference path for documented local materials, not a path derived from user input. The instruction also specifies a bundled immutable fallback for standalone installs."
      },
      {
        "id": "filesystem:SKILL.md:114:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.91,
        "reason": "This is a fixed Markdown link to a documented local reference or related skill, not a user-controlled filesystem operation. It does not provide a traversal primitive."
      },
      {
        "id": "filesystem:SKILL.md:115:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.91,
        "reason": "This is a fixed Markdown link to a documented local reference or related skill, not a user-controlled filesystem operation. It does not provide a traversal primitive."
      },
      {
        "id": "filesystem:SKILL.md:116:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.91,
        "reason": "This is a fixed Markdown link to a documented local reference or related skill, not a user-controlled filesystem operation. It does not provide a traversal primitive."
      },
      {
        "id": "filesystem:SKILL.md:117:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.91,
        "reason": "This is a fixed Markdown link to a documented local reference or related skill, not a user-controlled filesystem operation. It does not provide a traversal primitive."
      },
      {
        "id": "filesystem:SKILL.md:121:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.91,
        "reason": "This is a fixed Markdown link to a documented local reference or related skill, not a user-controlled filesystem operation. It does not provide a traversal primitive."
      },
      {
        "id": "filesystem:SKILL.md:122:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.91,
        "reason": "This is a fixed Markdown link to a documented local reference or related skill, not a user-controlled filesystem operation. It does not provide a traversal primitive."
      },
      {
        "id": "filesystem:SKILL.md:123:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.91,
        "reason": "This is a fixed Markdown link to a documented local reference or related skill, not a user-controlled filesystem operation. It does not provide a traversal primitive."
      },
      {
        "id": "filesystem:SKILL.md:124:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.91,
        "reason": "This is a fixed Markdown link to a documented local reference or related skill, not a user-controlled filesystem operation. It does not provide a traversal primitive."
      },
      {
        "id": "filesystem:SKILL.md:57:standard-device-file-access",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The line does not name or access a device file. The detector matched general filesystem reference syntax in Markdown."
      }
    ],
    "semantic_findings": [],
    "critical_findings": [],
    "high_findings": [],
    "medium_findings": [],
    "low_findings": [],
    "dangerous_patterns": [],
    "files_scanned": 2,
    "total_lines": 374,
    "audit_model": "claude",
    "audited_at": "2026-07-26T10:14:54.622Z",
    "agent_auto_install_policy": "allowed",
    "manual_install_policy": "allowed"
  },
  "content": {
    "user_title": "Audit an email send before release",
    "value_statement": "Email teams can miss consent, suppression, authentication, and claim risks before a campaign launches. This skill applies a structured SEND review and states the evidence, gaps, score state, and release verdict.",
    "seo_keywords": [
      "Claude",
      "Codex",
      "Claude Code",
      "email quality audit",
      "email campaign review",
      "deliverability audit",
      "consent verification",
      "unsubscribe compliance",
      "SEND scoring",
      "email release checklist"
    ],
    "actual_capabilities": [
      "Reviews one email program or planned send within a declared observation window.",
      "Evaluates 20 SEND criteria using dated evidence and confidence labels.",
      "Checks authentication, consent, suppressions, claims, engagement, and outcome evidence.",
      "Separates verified blockers from unknown or missing inputs.",
      "Produces SHIP, FIX, BLOCK, or UNDECIDED outcomes when evidence supports them.",
      "Explains measurement limits for open rates and Apple Mail Privacy Protection."
    ],
    "limitations": [
      "It does not send email or change provider settings.",
      "It cannot prove inbox placement from DNS records alone.",
      "It needs current consent, suppression, provider, and outcome evidence for a complete score.",
      "It does not replace legal advice or a formal compliance review."
    ],
    "use_cases": [
      {
        "title": "Release a promotional campaign",
        "description": "Check a planned promotion for authentication, consent, opt-out, and claim blockers before the marketing team sends it.",
        "target_user": "Email marketers"
      },
      {
        "title": "Assess newsletter program health",
        "description": "Review a newsletter over a defined period and identify evidence gaps, engagement caveats, and operational fixes.",
        "target_user": "Lifecycle managers"
      },
      {
        "title": "Prepare an audit record",
        "description": "Create an evidence-based readiness assessment that separates verified controls from unknown inputs for internal review.",
        "target_user": "Compliance and operations teams"
      }
    ],
    "prompt_templates": [
      {
        "title": "Review a newsletter",
        "scenario": "Beginner",
        "prompt": "Audit this newsletter for the last 90 days. I will provide provider reports, consent records, suppression status, and campaign results."
      },
      {
        "title": "Check a promotional send",
        "scenario": "Intermediate",
        "prompt": "Review this promotional email before release. Check DMARC, consent events, live suppressions, rendered copy, and order evidence. Mark missing evidence as Unknown."
      },
      {
        "title": "Compare provider cohorts",
        "scenario": "Advanced",
        "prompt": "Audit this retention program across providers for the declared window. Reconcile cohorts, segment Apple Mail Privacy Protection exposure, and assess direct actions separately from opens."
      },
      {
        "title": "Request a release trace",
        "scenario": "Expert",
        "prompt": "Perform a SEND audit for this cold-outbound program. Provide a trace for each veto check, list source dates and confidence, and return UNDECIDED if evidence is incomplete."
      }
    ],
    "output_examples": [
      {
        "input": "A newsletter has aligned authentication, current suppressions, consent records, and complete performance data.",
        "output": [
          "Verdict: SHIP",
          "Score: 81 with high confidence",
          "No verified vetoes found",
          "Continue provider monitoring and preserve evidence sources"
        ]
      },
      {
        "input": "A promotional send has no consent provenance and no current suppression export.",
        "output": [
          "Verdict: UNDECIDED",
          "Score state: NOT_SCORED",
          "Unknown inputs: consent provenance and live suppression status",
          "Next step: provide dated consent events and a current suppression replay"
        ]
      },
      {
        "input": "A campaign uses a verified purchased list and ignores an opt-out record.",
        "output": [
          "Verdict: BLOCK",
          "Verified controls failed: list provenance and opt-out handling",
          "Do not send until the list is remediated and suppressions are honored"
        ]
      }
    ],
    "best_practices": [
      "Provide dated source evidence for each claim, metric, and control.",
      "Declare the program type, market, provider, and observation window before scoring.",
      "Treat unknown evidence as unknown instead of assuming a control passed."
    ],
    "anti_patterns": [
      "Do not use open rate alone to claim recipient attention or campaign success.",
      "Do not treat missing consent records as proof that consent exists.",
      "Do not request a release verdict without current suppression and claim evidence."
    ],
    "faq": [
      {
        "question": "Does this skill send email?",
        "answer": "No. It audits readiness and does not send messages or change provider settings."
      },
      {
        "question": "What evidence should I provide?",
        "answer": "Provide authentication data, consent and suppression records, rendered content, provider reports, and outcome records."
      },
      {
        "question": "Can it review a single campaign?",
        "answer": "Yes. It can perform a send-only review and identifies the evidence needed for a complete program score."
      },
      {
        "question": "What happens when evidence is missing?",
        "answer": "The skill marks the affected item as Unknown and may return an UNDECIDED or NOT_SCORED result."
      },
      {
        "question": "Does it measure inbox placement?",
        "answer": "It reviews supplied placement and provider evidence, but DNS data alone cannot prove inbox placement."
      },
      {
        "question": "Is this legal compliance advice?",
        "answer": "No. It supports operational review and does not replace legal or regulatory advice."
      }
    ]
  },
  "file_structure": [
    {
      "name": "references",
      "type": "dir",
      "path": "references",
      "children": [
        {
          "name": "auditor-runtime.md",
          "type": "file",
          "path": "references/auditor-runtime.md",
          "lines": 249
        }
      ]
    },
    {
      "name": "SKILL.md",
      "type": "file",
      "path": "SKILL.md",
      "lines": 125
    }
  ]
}
rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first.Stars: 194kUpdated Claude CodeCodexVerifiedInstall