4-step-program

Pass

Audited by Gen Agent Trust Hub on Feb 25, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it processes untrusted data from GitHub issues.
  • Ingestion points: The workflow uses 'gh issue view' to read the full body of issues which are used to generate delegation instructions for other agents.
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands within the issue body are provided in the delegation logic.
  • Capability inventory: The skill has the ability to delegate tasks using 'assign_task' and can write permanent reviews to GitHub using 'mcp__github__create_pull_request_review'.
  • Sanitization: There is no requirement or logic specified for the sanitization of issue text before it is passed into the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 25, 2026, 11:31 AM