receiving-code-review

Pass

Audited by Gen Agent Trust Hub on Jun 23, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill is designed to process feedback from external reviewers, which constitutes untrusted data that could contain malicious instructions.
  • Ingestion points: GitHub Pull Request comments and external reviewer feedback (referenced in 'Source-Specific Handling').
  • Boundary markers: None specified to delimit external content from internal instructions.
  • Capability inventory: File system modification (implementation of code fixes) and GitHub API interaction (gh api).
  • Sanitization: No explicit sanitization or validation of the feedback content is described before the agent processes or implements it.
  • [COMMAND_EXECUTION]: Automated Tool Usage. The skill provides specific patterns for interacting with the GitHub API using the gh command-line tool (gh api repos/{owner}/{repo}/pulls/{pr}/comments/{id}/replies). This capability allows the agent to take actions in external repositories based on the context of the code review.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 23, 2026, 08:03 AM
Security Audit — agent-trust-hub — receiving-code-review