gh-address-comments

Pass

Audited by Gen Agent Trust Hub on Jul 21, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/fetch_comments.py executes GitHub CLI (gh) commands using the subprocess.run function. The implementation correctly uses argument lists and the -F parameter for variable interpolation, which effectively mitigates common command injection risks.
  • [PROMPT_INJECTION]: The skill processes untrusted content from GitHub pull request comments and review threads, creating a potential surface for indirect prompt injection attacks where malicious instructions in a comment could influence the agent's actions during code modification.
  • Ingestion points: The scripts/fetch_comments.py script retrieves body content from PR comments, reviews, and review threads via GitHub's GraphQL API.
  • Boundary markers: The instructions do not provide the agent with specific delimiters or warnings to treat the fetched comment text as untrusted data or to ignore embedded instructions.
  • Capability inventory: The agent is granted the capability to modify the local codebase to implement the fixes requested in the feedback.
  • Sanitization: There is no evidence of sanitization, filtering, or validation performed on the retrieved comment content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 21, 2026, 12:23 AM
Security Audit — agent-trust-hub — gh-address-comments