github-pull-request-review-resolve

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the GitHub CLI (gh) for authentication, metadata retrieval, and API interactions, as well as Git for committing and pushing code updates. Evidence is located in SKILL.md workflow steps 1, 2, 5, and 6.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted pull request comments and review threads to determine its actions.\n
  • Ingestion points: Pull request comments and review threads (SKILL.md, Step 2).\n
  • Boundary markers: None present to isolate untrusted data.\n
  • Capability inventory: File modification, local command execution, and remote pushing (SKILL.md, Steps 4 and 5).\n
  • Sanitization: No sanitization or validation of comment content is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 10:18 PM