pull-requests

Pass

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [Indirect Prompt Injection Surface]: The skill workflow involves reading and responding to pull request review comments, which are external data sources. This presents a potential surface where external instructions could influence the agent's behavior. To mitigate this, the skill incorporates a manual review step where the agent must present a plan to the user for approval before taking action, providing a human-in-the-loop control mechanism.
  • [Command Execution]: The skill includes instructions for using the GitHub CLI (gh) to interact with pull requests via both REST and GraphQL APIs. These commands enable standard operations like listing comments, creating pull requests, and resolving threads, which are appropriate for the skill's purpose of streamlining repository contribution workflows.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 5, 2026, 04:26 AM
Security Audit — agent-trust-hub — pull-requests