Skip to content

AL-JANEF/janef-forge / skills/security/skill-security-audit

skill-security-audit

Flagged

Gate before adopting any external agent skill, plugin, hook, script, installer, or MCP package: provenance and license review, deterministic static triage (scripts/audit_skill.py), optional NVIDIA SkillSpector scan, and manual review for prompt injection, credential access, exfiltration, and destructive commands. Fails closed on unresolved HIGH/CRITICAL findings or incomplete scans; scanning is a control, not proof of safety.

FileKindSize
SKILL.mdskill md3.1 KB
capability.jsonconfig2.1 KB

capability.json

View on GitHub
{
  "id": "skill-security-audit",
  "name": "External Skill Security Audit",
  "version": "2.0.0",
  "domain": "security",
  "description": "Gate before adopting any external agent skill, plugin, hook, script, installer, or MCP package: provenance and license review, deterministic static triage (scripts/audit_skill.py), optional NVIDIA SkillSpector scan, and manual review for prompt injection, credential access, exfiltration, and destructive commands. Fails closed on unresolved HIGH/CRITICAL findings or incomplete scans; scanning is a control, not proof of safety.",
  "triggers": [
    "external skill",
    "third-party skill",
    "third party skill",
    "install a skill",
    "install this skill",
    "install the skill",
    "plugin install",
    "install plugin",
    "install the plugin",
    "install this plugin",
    "mcp server",
    "mcp package",
    "mcp servers",
    "untrusted skill",
    "skillspector",
    "prompt injection",
    "hook",
    "hooks",
    "adopt this skill",
    "marketplace",
    "new plugin",
    "is this skill safe",
    "is this plugin safe",
    "skill from github",
    "agent skill",
    "skills repo",
    "vendor a skill",
    "claude plugin",
    "codex plugin",
    "extension",
    "ignore all previous instructions",
    "ignore previous instructions",
    "previous instructions",
    "system prompt"
  ],
  "negative_triggers": [],
  "risk_level": "high",
  "context_cost": "medium",
  "requires": [],
  "optional_with": [
    "secrets-guard"
  ],
  "conflicts_with": [],
  "verification_requirements": [
    "scanner or static triage output attached, or explicitly NOT RUN with the candidate treated as not approved",
    "provenance (source, version or commit, license) recorded",
    "no HIGH or CRITICAL finding left unresolved before adoption"
  ],
  "supported_hosts": [
    "claude-code",
    "codex"
  ],
  "references": [],
  "status": "stable",
  "responsibilities": [
    "external-skill-gating",
    "supply-chain-review-for-agent-content"
  ],
  "priority": 64,
  "provenance": [
    "agent-engineering-stack 1.1.0 skill-security-audit and scripts/audit-skill.py"
  ]
}
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: 471kUpdated 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: 471kUpdated Claude CodeCodexVerifiedInstall
rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics.Stars: 471kUpdated 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