Skip to content

aiskillstore/marketplace / skills/aaron-he-zhu/placement-exclusion-manager

placement-exclusion-manager

Verified

Use when the user asks to "build my brand-safety exclusion lists", "set placement / topic / content exclusions before launch", "add network and audience exclusions", or "prep the A1 brand-safety evidence for the auditor"; produces a placement/network exclusion list, a content-suitability & sensitive-topic block list, an audience/negative-audience exclusion set, and a packaged A1 brand/placement-safety evidence file for the gate. Not for building the audiences you target — use audience-segment-builder; not for computing the RQS or issuing the A1 verdict — use ad-account-auditor. 品牌安全/排除位置/否定受众列表

FileKindSize
SKILL.mdskill md9.3 KB
skill-report.jsonconfig37.4 KB

skill-report.json

View on GitHub
{
  "schema_version": "2.0",
  "meta": {
    "generated_at": "2026-07-27T11:38:07.937Z",
    "slug": "aaron-he-zhu-placement-exclusion-manager",
    "source_url": "https://github.com/aaron-he-zhu/aaron-marketing-skills/tree/main/ad/activate/placement-exclusion-manager",
    "source_ref": "main",
    "model": "claude",
    "analysis_version": "3.0.0",
    "source_type": "community",
    "content_hash": "74cc02f342a1932d98d4a3aa8bb3a0d48c87c85f1dd088804c43483f88a86f00",
    "tree_hash": "360bef316d9270c81ff41e64bce2e3333c068c08adeae9fa9b7b114f84d9cc48",
    "provenance": {
      "model_effective": "claude",
      "fallback_chain": [
        {
          "agent": "codex",
          "outcome": "failed",
          "error": "2026-07-27T11:38:08.042383Z ERROR codex_models_manager::manager: failed to refresh available models: Missing environment variable: `HELM_API_KEY`.\n2026-07-27T11:38:08.073377Z 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": "872fb912bb0b55629302d813e22b01895c09c809"
  },
  "skill": {
    "name": "placement-exclusion-manager",
    "description": "Build placement, network, and content-suitability exclusion plans from campaign goals, brand-safety constraints, and user-provided placement reports.",
    "summary": "Create evidence-backed advertising exclusion plans before campaign launch.",
    "icon": "📦",
    "version": "19.0.0",
    "author": "aaron-he-zhu",
    "license": "Apache-2.0",
    "tags": [
      "brand safety",
      "advertising",
      "placement exclusions",
      "campaign governance",
      "content suitability"
    ],
    "supported_tools": [
      "claude",
      "codex",
      "claude-code"
    ],
    "risk_factors": [
      "external_commands",
      "network",
      "filesystem"
    ],
    "category": "security"
  },
  "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 formatting, documentation links, and fixed skill memory paths. The skill gives planning guidance for advertising exclusions and explicitly instructs agents to treat imported reports as untrusted input. No executable commands, data-exfiltration intent, or prompt-injection attempt was found.",
    "remediation": [
      {
        "issue": "Static scanners may mistake Markdown code spans and fenced examples for shell execution.",
        "suggestion": "Use prose or clearly labelled non-executable examples where practical, and keep command-like syntax out of documentation headings.",
        "severity": "low"
      },
      {
        "issue": "Relative repository links trigger path-traversal heuristics.",
        "suggestion": "Document that links are fixed internal references and that output paths are not constructed from untrusted input.",
        "severity": "low"
      }
    ],
    "risk_factor_evidence": [
      {
        "factor": "external_commands",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 18,
            "line_end": 18
          },
          {
            "file": "SKILL.md",
            "line_start": 22,
            "line_end": 24
          },
          {
            "file": "SKILL.md",
            "line_start": 24,
            "line_end": 26
          },
          {
            "file": "SKILL.md",
            "line_start": 26,
            "line_end": 28
          },
          {
            "file": "SKILL.md",
            "line_start": 28,
            "line_end": 30
          },
          {
            "file": "SKILL.md",
            "line_start": 30,
            "line_end": 32
          },
          {
            "file": "SKILL.md",
            "line_start": 32,
            "line_end": 39
          },
          {
            "file": "SKILL.md",
            "line_start": 39,
            "line_end": 40
          },
          {
            "file": "SKILL.md",
            "line_start": 40,
            "line_end": 40
          },
          {
            "file": "SKILL.md",
            "line_start": 41,
            "line_end": 50
          },
          {
            "file": "SKILL.md",
            "line_start": 50,
            "line_end": 50
          },
          {
            "file": "SKILL.md",
            "line_start": 56,
            "line_end": 57
          },
          {
            "file": "SKILL.md",
            "line_start": 57,
            "line_end": 68
          },
          {
            "file": "SKILL.md",
            "line_start": 68,
            "line_end": 74
          },
          {
            "file": "SKILL.md",
            "line_start": 74,
            "line_end": 79
          },
          {
            "file": "SKILL.md",
            "line_start": 79,
            "line_end": 82
          }
        ]
      },
      {
        "factor": "network",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 10,
            "line_end": 10
          },
          {
            "file": "SKILL.md",
            "line_start": 13,
            "line_end": 13
          }
        ]
      },
      {
        "factor": "filesystem",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 36,
            "line_end": 36
          },
          {
            "file": "SKILL.md",
            "line_start": 38,
            "line_end": 38
          },
          {
            "file": "SKILL.md",
            "line_start": 42,
            "line_end": 42
          },
          {
            "file": "SKILL.md",
            "line_start": 46,
            "line_end": 46
          },
          {
            "file": "SKILL.md",
            "line_start": 50,
            "line_end": 50
          },
          {
            "file": "SKILL.md",
            "line_start": 54,
            "line_end": 54
          },
          {
            "file": "SKILL.md",
            "line_start": 61,
            "line_end": 61
          },
          {
            "file": "SKILL.md",
            "line_start": 64,
            "line_end": 64
          },
          {
            "file": "SKILL.md",
            "line_start": 68,
            "line_end": 68
          },
          {
            "file": "SKILL.md",
            "line_start": 72,
            "line_end": 72
          },
          {
            "file": "SKILL.md",
            "line_start": 73,
            "line_end": 73
          },
          {
            "file": "SKILL.md",
            "line_start": 74,
            "line_end": 74
          },
          {
            "file": "SKILL.md",
            "line_start": 75,
            "line_end": 75
          },
          {
            "file": "SKILL.md",
            "line_start": 79,
            "line_end": 79
          },
          {
            "file": "SKILL.md",
            "line_start": 81,
            "line_end": 81
          },
          {
            "file": "SKILL.md",
            "line_start": 83,
            "line_end": 83
          }
        ]
      }
    ],
    "static_findings": [
      {
        "id": "external_commands:SKILL.md:18:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 18,
        "line_end": 18,
        "snippet": "Builds the brand-safety and exclusion lists that gate spend before a campaign goes live — placement/"
      },
      {
        "id": "external_commands:SKILL.md:22:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 22,
        "line_end": 24,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:24:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 24,
        "line_end": 26,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:26:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 26,
        "line_end": 28,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:28:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 28,
        "line_end": 30,
        "snippet": "```"
      },
      {
        "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": 32,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:32:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 32,
        "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": 40,
        "snippet": "- **Writes**: a user-facing exclusion plan, the A1 evidence file, and a reusable summary to `memory/"
      },
      {
        "id": "external_commands:SKILL.md:40:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 40,
        "line_end": 40,
        "snippet": "- **Promotes**: chosen brand-safety constraints, exclusion decisions, and any missing placements rep"
      },
      {
        "id": "external_commands:SKILL.md:41:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 41,
        "line_end": 50,
        "snippet": "- **Done when**: placement/network exclusions are specified against a named goal; content-suitabilit"
      },
      {
        "id": "external_commands:SKILL.md:50:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 50,
        "line_end": 50,
        "snippet": "Use `~~ad platform` (own-account manual export — native ad-manager **placements report** plus campai"
      },
      {
        "id": "external_commands:SKILL.md:56:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 56,
        "line_end": 57,
        "snippet": "1. **Confirm profile and brand-safety constraints** — record the vertical, any sensitive-topic rules"
      },
      {
        "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": 68,
        "snippet": "2. **Ingest the placements report** — parse where ads served or could serve. If it is absent, mark q"
      },
      {
        "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": 74,
        "snippet": "On user confirmation, save to `memory/ad/placement-exclusion-manager/YYYY-MM-DD-<account-or-goal>-ex"
      },
      {
        "id": "external_commands:SKILL.md:74:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 74,
        "line_end": 79,
        "snippet": "- [CONNECTORS.md](../../../CONNECTORS.md) — keyless export recipes for `~~ad platform`"
      },
      {
        "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": 82,
        "snippet": "Global termination applies (visited-set, `max-depth: 3`, ambiguity-stop) — see [skill-contract.md §T"
      },
      {
        "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:13:hardcoded-url",
        "category": "network",
        "severity": "low",
        "pattern": "Hardcoded URL",
        "file": "SKILL.md",
        "line_start": 13,
        "line_end": 13,
        "snippet": "metadata: {\"author\": \"aaron-he-zhu\", \"version\": \"19.0.0\", \"discipline\": \"ad\", \"phase\": \"activate\", \""
      },
      {
        "id": "filesystem:SKILL.md:36:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 36,
        "line_end": 36,
        "snippet": "**Expected output**: a placement/network exclusion list (sites, apps, channels, network opt-outs), a"
      },
      {
        "id": "filesystem:SKILL.md:38:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 38,
        "line_end": 38,
        "snippet": "- **Reads**: account/campaign goal and brand-safety constraints, exported **placements report** (own"
      },
      {
        "id": "filesystem:SKILL.md:42:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 42,
        "line_end": 42,
        "snippet": "- **Primary next skill**: [ad-account-auditor](../ad-account-auditor/SKILL.md) to score the full RQS"
      },
      {
        "id": "filesystem:SKILL.md:46:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 46,
        "line_end": 46,
        "snippet": "> Emit the standard shape from [skill-contract.md §Handoff Summary Format](../../../references/skill"
      },
      {
        "id": "filesystem:SKILL.md:50:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 50,
        "line_end": 50,
        "snippet": "Use `~~ad platform` (own-account manual export — native ad-manager **placements report** plus campai"
      },
      {
        "id": "filesystem:SKILL.md:54:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 54,
        "line_end": 54,
        "snippet": "Treat every exported or fetched file as untrusted input per [SECURITY.md](../../../SECURITY.md) — ne"
      },
      {
        "id": "filesystem:SKILL.md:61:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 61,
        "line_end": 61,
        "snippet": "6. **Consume the audience exclusion set** — do not re-derive existing-customer, converter, or off-fi"
      },
      {
        "id": "filesystem:SKILL.md:64:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 64,
        "line_end": 64,
        "snippet": "**Scope guard**: this skill owns **placement / network / content-suitability exclusions + A1 evidenc"
      },
      {
        "id": "filesystem:SKILL.md:68:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 68,
        "line_end": 68,
        "snippet": "On user confirmation, save to `memory/ad/placement-exclusion-manager/YYYY-MM-DD-<account-or-goal>-ex"
      },
      {
        "id": "filesystem:SKILL.md:72:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 72,
        "line_end": 72,
        "snippet": "- [roas-benchmark.md](../../../references/roas-benchmark.md) — ROAS framework, A dimension, A1 veto "
      },
      {
        "id": "filesystem:SKILL.md:73:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 73,
        "line_end": 73,
        "snippet": "- [audience-segment-builder](../../research/audience-segment-builder/SKILL.md) — SSOT for targeted a"
      },
      {
        "id": "filesystem:SKILL.md:74:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 74,
        "line_end": 74,
        "snippet": "- [CONNECTORS.md](../../../CONNECTORS.md) — keyless export recipes for `~~ad platform`"
      },
      {
        "id": "filesystem:SKILL.md:75:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 75,
        "line_end": 75,
        "snippet": "- [SECURITY.md](../../../SECURITY.md) — treat exports as untrusted input"
      },
      {
        "id": "filesystem:SKILL.md:79:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 79,
        "line_end": 79,
        "snippet": "Global termination applies (visited-set, `max-depth: 3`, ambiguity-stop) — see [skill-contract.md §T"
      },
      {
        "id": "filesystem:SKILL.md:81:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 81,
        "line_end": 81,
        "snippet": "- **Primary**: [ad-account-auditor](../ad-account-auditor/SKILL.md) — score the full RQS and issue t"
      },
      {
        "id": "filesystem:SKILL.md:83:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 83,
        "line_end": 83,
        "snippet": "- **If targeted audiences are not yet defined**: [audience-segment-builder](../../research/audience-"
      }
    ],
    "finding_verdicts": [
      {
        "id": "external_commands:SKILL.md:18:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The matched text is Markdown inline or fenced code formatting in a documentation-only skill. It does not invoke a shell, Ruby, or any executable command."
      },
      {
        "id": "external_commands:SKILL.md:22:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The matched text is Markdown inline or fenced code formatting in a documentation-only skill. It does not invoke a shell, Ruby, or any executable command."
      },
      {
        "id": "external_commands:SKILL.md:24:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The matched text is Markdown inline or fenced code formatting in a documentation-only skill. It does not invoke a shell, Ruby, or any executable command."
      },
      {
        "id": "external_commands:SKILL.md:26:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The matched text is Markdown inline or fenced code formatting in a documentation-only skill. It does not invoke a shell, Ruby, or any executable command."
      },
      {
        "id": "external_commands:SKILL.md:28:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The matched text is Markdown inline or fenced code formatting in a documentation-only skill. It does not invoke a shell, Ruby, or any executable command."
      },
      {
        "id": "external_commands:SKILL.md:30:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The matched text is Markdown inline or fenced code formatting in a documentation-only skill. It does not invoke a shell, Ruby, or any executable command."
      },
      {
        "id": "external_commands:SKILL.md:32:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The matched text is Markdown inline or fenced code formatting in a documentation-only skill. It does not invoke a shell, Ruby, or any executable command."
      },
      {
        "id": "external_commands:SKILL.md:39:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The matched text is Markdown inline or fenced code formatting in a documentation-only skill. It does not invoke a shell, Ruby, or any executable command."
      },
      {
        "id": "external_commands:SKILL.md:40:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The matched text is Markdown inline or fenced code formatting in a documentation-only skill. It does not invoke a shell, Ruby, or any executable command."
      },
      {
        "id": "external_commands:SKILL.md:41:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The matched text is Markdown inline or fenced code formatting in a documentation-only skill. It does not invoke a shell, Ruby, or any executable command."
      },
      {
        "id": "external_commands:SKILL.md:50:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The matched text is Markdown inline or fenced code formatting in a documentation-only skill. It does not invoke a shell, Ruby, or any executable command."
      },
      {
        "id": "external_commands:SKILL.md:56:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The matched text is Markdown inline or fenced code formatting in a documentation-only skill. It does not invoke a shell, Ruby, or any executable command."
      },
      {
        "id": "external_commands:SKILL.md:57:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The matched text is Markdown inline or fenced code formatting in a documentation-only skill. It does not invoke a shell, Ruby, or any executable command."
      },
      {
        "id": "external_commands:SKILL.md:68:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The matched text is Markdown inline or fenced code formatting in a documentation-only skill. It does not invoke a shell, Ruby, or any executable command."
      },
      {
        "id": "external_commands:SKILL.md:74:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The matched text is Markdown inline or fenced code formatting in a documentation-only skill. It does not invoke a shell, Ruby, or any executable command."
      },
      {
        "id": "external_commands:SKILL.md:79:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The matched text is Markdown inline or fenced code formatting in a documentation-only skill. It does not invoke a shell, Ruby, or any executable command."
      },
      {
        "id": "network:SKILL.md:10:hardcoded-url",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "This is a homepage URL or metadata value, not a network request. The skill contains no instruction or code that sends data to that URL."
      },
      {
        "id": "network:SKILL.md:13:hardcoded-url",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "This is a homepage URL or metadata value, not a network request. The skill contains no instruction or code that sends data to that URL."
      },
      {
        "id": "filesystem:SKILL.md:36:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The match is a relative Markdown link to repository documentation or a fixed memory output location. It is not user-controlled path resolution and provides no traversal primitive."
      },
      {
        "id": "filesystem:SKILL.md:38:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The match is a relative Markdown link to repository documentation or a fixed memory output location. It is not user-controlled path resolution and provides no traversal primitive."
      },
      {
        "id": "filesystem:SKILL.md:42:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The match is a relative Markdown link to repository documentation or a fixed memory output location. It is not user-controlled path resolution and provides no traversal primitive."
      },
      {
        "id": "filesystem:SKILL.md:46:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The match is a relative Markdown link to repository documentation or a fixed memory output location. It is not user-controlled path resolution and provides no traversal primitive."
      },
      {
        "id": "filesystem:SKILL.md:50:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The match is a relative Markdown link to repository documentation or a fixed memory output location. It is not user-controlled path resolution and provides no traversal primitive."
      },
      {
        "id": "filesystem:SKILL.md:54:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The match is a relative Markdown link to repository documentation or a fixed memory output location. It is not user-controlled path resolution and provides no traversal primitive."
      },
      {
        "id": "filesystem:SKILL.md:61:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The match is a relative Markdown link to repository documentation or a fixed memory output location. It is not user-controlled path resolution and provides no traversal primitive."
      },
      {
        "id": "filesystem:SKILL.md:64:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The match is a relative Markdown link to repository documentation or a fixed memory output location. It is not user-controlled path resolution and provides no traversal primitive."
      },
      {
        "id": "filesystem:SKILL.md:68:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The match is a relative Markdown link to repository documentation or a fixed memory output location. It is not user-controlled path resolution and provides no traversal primitive."
      },
      {
        "id": "filesystem:SKILL.md:72:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The match is a relative Markdown link to repository documentation or a fixed memory output location. It is not user-controlled path resolution and provides no traversal primitive."
      },
      {
        "id": "filesystem:SKILL.md:73:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The match is a relative Markdown link to repository documentation or a fixed memory output location. It is not user-controlled path resolution and provides no traversal primitive."
      },
      {
        "id": "filesystem:SKILL.md:74:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The match is a relative Markdown link to repository documentation or a fixed memory output location. It is not user-controlled path resolution and provides no traversal primitive."
      },
      {
        "id": "filesystem:SKILL.md:75:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The match is a relative Markdown link to repository documentation or a fixed memory output location. It is not user-controlled path resolution and provides no traversal primitive."
      },
      {
        "id": "filesystem:SKILL.md:79:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The match is a relative Markdown link to repository documentation or a fixed memory output location. It is not user-controlled path resolution and provides no traversal primitive."
      },
      {
        "id": "filesystem:SKILL.md:81:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The match is a relative Markdown link to repository documentation or a fixed memory output location. It is not user-controlled path resolution and provides no traversal primitive."
      },
      {
        "id": "filesystem:SKILL.md:83:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The match is a relative Markdown link to repository documentation or a fixed memory output location. It is not user-controlled path resolution and provides no traversal primitive."
      }
    ],
    "semantic_findings": [],
    "critical_findings": [],
    "high_findings": [],
    "medium_findings": [],
    "low_findings": [],
    "dangerous_patterns": [],
    "files_scanned": 1,
    "total_lines": 84,
    "audit_model": "claude",
    "audited_at": "2026-07-27T11:38:07.937Z",
    "agent_auto_install_policy": "allowed",
    "manual_install_policy": "allowed"
  },
  "content": {
    "user_title": "Build safer advertising placement exclusions",
    "value_statement": "Campaign teams need clear controls to prevent ads from appearing in unsuitable placements. This skill creates an evidence-backed exclusion plan and packages the material for an A1 brand-safety review.",
    "seo_keywords": [
      "Claude",
      "Codex",
      "Claude Code",
      "placement exclusion manager",
      "advertising brand safety",
      "content suitability",
      "network opt-outs",
      "placement report analysis",
      "campaign exclusions",
      "A1 evidence"
    ],
    "actual_capabilities": [
      "Creates site, app, channel, and network exclusion recommendations from a placement report.",
      "Lists content-suitability tiers and sensitive-topic blocks that match stated brand constraints.",
      "Separates measured placement findings from user-provided brand-safety rules.",
      "Records reach-versus-safety tradeoffs for network participation decisions.",
      "Packages placement references and rationales as A1 evidence for a separate auditor.",
      "Identifies a missing placement report and stops with a request for input."
    ],
    "limitations": [
      "It does not access advertising accounts or export reports for the user.",
      "It cannot verify current platform settings without user-provided evidence.",
      "It does not create audience suppression segments or targeted audiences.",
      "It does not issue an A1 verdict or calculate an account quality score."
    ],
    "use_cases": [
      {
        "title": "Prepare a launch exclusion plan",
        "description": "Turn a new campaign goal and brand rules into placement, network, and content exclusions before spend begins.",
        "target_user": "Paid media manager"
      },
      {
        "title": "Review unsafe placements",
        "description": "Use a placement report to document low-quality, irrelevant, or off-brand placements with concise rationales.",
        "target_user": "Performance marketing analyst"
      },
      {
        "title": "Assemble audit evidence",
        "description": "Package placement evidence and exclusion decisions for a separate brand-safety or account audit.",
        "target_user": "Marketing compliance reviewer"
      }
    ],
    "prompt_templates": [
      {
        "title": "Start an exclusion plan",
        "scenario": "Beginner",
        "prompt": "Build brand-safety exclusion lists for my ecommerce launch on Google Ads. Exclude sensitive news and competitor placements."
      },
      {
        "title": "Review a placement report",
        "scenario": "Intermediate",
        "prompt": "Review this placement report for my B2B campaign. List unsuitable sites and apps, label each finding as measured, and explain the exclusion."
      },
      {
        "title": "Set network controls",
        "scenario": "Advanced",
        "prompt": "Recommend Search partner, Display expansion, and Audience network opt-outs for a lead-generation campaign. Explain each reach and safety tradeoff."
      },
      {
        "title": "Package audit evidence",
        "scenario": "Advanced",
        "prompt": "Create A1 brand-safety evidence from this placements report and these exclusion decisions. Do not assign an A1 verdict."
      }
    ],
    "output_examples": [
      {
        "input": "Exclude placements that conflict with a family-safe product launch.",
        "output": [
          "Placement exclusions: identified unsuitable sites and apps with reasons.",
          "Content blocks: sensitive news, tragedy adjacency, and adult themes.",
          "Evidence status: requires the placement report before A1 evidence is complete."
        ]
      },
      {
        "input": "Prepare network exclusions for a tightly controlled B2B campaign.",
        "output": [
          "Network decision: evaluate Search partners, Display expansion, and Audience network separately.",
          "Rationale: prioritize control and documented brand suitability over maximum reach.",
          "Handoff: package decisions for the account auditor."
        ]
      }
    ],
    "best_practices": [
      "Provide a recent placement report and the campaign goal before requesting exclusions.",
      "State non-negotiable brand-safety rules separately from performance preferences.",
      "Review exclusion decisions with the account owner before saving or applying them."
    ],
    "anti_patterns": [
      "Do not infer a safe placement list when the placement report is missing.",
      "Do not treat audience exclusions as placement exclusions or recreate another skill’s audience set.",
      "Do not use the plan as a substitute for platform review or an auditor’s verdict."
    ],
    "faq": [
      {
        "question": "Does this skill connect to my ad account?",
        "answer": "No. Provide your own account exports or placement reports."
      },
      {
        "question": "What data should I provide?",
        "answer": "Provide a campaign goal, platforms, brand-safety constraints, and a placement report when available."
      },
      {
        "question": "Can it create audience exclusions?",
        "answer": "No. It references an existing audience exclusion set and does not create suppression segments."
      },
      {
        "question": "Can it decide whether my account passes A1?",
        "answer": "No. It prepares evidence for a separate account auditor."
      },
      {
        "question": "What happens if I have no placement report?",
        "answer": "The skill marks qualified evidence as unknown and requests the report instead of guessing."
      },
      {
        "question": "Can it apply exclusions in an ad platform?",
        "answer": "No. It produces recommendations and evidence. You must review and apply settings in your platform."
      }
    ]
  },
  "file_structure": [
    {
      "name": "SKILL.md",
      "type": "file",
      "path": "SKILL.md",
      "lines": 84
    }
  ]
}
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