janitor-audit

Pass

Audited by Gen Agent Trust Hub on May 12, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local shell script at ~/.claude/skills/skills-janitor/scripts/scan.sh. This execution is the primary mechanism for the skill's stated purpose of auditing and inventorying installed skills.
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection because it ingests and processes metadata (frontmatter and body content) from other installed skills to generate its summary report.
  • Ingestion points: Internal platform directories including ~/.claude/skills/, ./.claude/skills/, ~/.claude/plugins/, ~/.claude/sources/, and account-specific plugin paths.
  • Boundary markers: None identified in the provided instructions; data is processed directly into the output context.
  • Capability inventory: Local shell script execution via bash and file system read access.
  • Sanitization: There is no mention of sanitization or validation of the content retrieved from scanned skills before presenting it to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 12, 2026, 08:48 PM
Security Audit — agent-trust-hub — janitor-audit