skills/angusfretwell/skills/afk-loop/Gen Agent Trust Hub

afk-loop

Pass

Audited by Gen Agent Trust Hub on Jul 11, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted data from an issue tracker and pull request comments as primary instructions for sub-agents, creating a risk for indirect prompt injection.
  • Ingestion points: The skill fetches issue titles, bodies, and comments, and pull request discussion logs to serve as specifications.
  • Boundary markers: The skill lacks explicit delimiters or instructions to isolate untrusted external content from the core logic, which may lead the agent to follow instructions embedded in issue data.
  • Capability inventory: Sub-agents have permissions to write code, execute project test suites (via /tdd and full check suites), commit changes, and open pull requests.
  • Sanitization: There is no evidence of sanitization or validation of external content present in the skill's instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 11, 2026, 10:21 AM
Security Audit — agent-trust-hub — afk-loop