janitor-report

Pass

Audited by Gen Agent Trust Hub on May 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONNO_CODE
Full Analysis
  • [COMMAND_EXECUTION]: The skill triggers the execution of local bash scripts (scan.sh, lint.sh, and detect_dupes.sh) located within the user's home directory (~/.claude/skills/skills-janitor/scripts/). These scripts are used to automate the inventory and health check process.
  • [DATA_EXPOSURE]: The skill accesses local file system structures and skill metadata, including symlinks, file contents, and frontmatter fields, to identify broken links or duplicate skills. This data access is aligned with the skill's primary function as a maintenance tool.
  • [NO_CODE]: The core logic for the analysis (scanning, linting, and duplication detection) resides in external shell scripts rather than within the skill's own instructions or embedded code blocks.
Audit Metadata
Risk Level
SAFE
Analyzed
May 12, 2026, 08:48 PM
Security Audit — agent-trust-hub — janitor-report