check-readiness

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill processes external, untrusted data from GitHub issue bodies and comments via the 'gh' tool, which can influence the agent's readiness assessment and follow-up prompts.\n
  • Ingestion points: GitHub issue metadata and user-generated comments fetched in Step 1 of the workflow.\n
  • Boundary markers: No explicit delimiters or instructions are specified to isolate untrusted data from the agent's internal logic.\n
  • Capability inventory: The skill can invoke '$coderabbit-cli', '$autofix', and 'merge-it' (for PR and merge management).\n
  • Sanitization: No input validation or sanitization is performed on the ingested text.\n- [COMMAND_EXECUTION]: Autonomous Lifecycle Management. The skill is designed to autonomously execute 'git commit' and 'git push' if they are the remaining blockers for a PR. Furthermore, it implements a follow-up routing system where brief user responses (e.g., 'y', 'yes', 'ok') trigger significant automated workflows, potentially leading to unintended consequences if the context was poisoned by malicious issue data.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 09:44 PM
Security Audit — agent-trust-hub — check-readiness