artifact-janitor
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- COMMAND_EXECUTION (SAFE): The skill contains a shell script (scripts/deep-clean.sh) that uses 'rm -rf' to delete specific, hardcoded artifact directories. This is the intended primary function of the skill and is implemented with safety checks and dry-run capabilities.
- DATA_EXPOSURE & EXFILTRATION (SAFE): The documentation explicitly warns against deleting sensitive files such as .env or .git directories. No network requests or data exfiltration patterns were found.
- PROMPT_INJECTION (SAFE): No instructions attempting to bypass safety filters or override agent behavior were identified in the markdown or script files.
Audit Metadata