skills/ceilidhboy/skills/pr-review/Gen Agent Trust Hub

pr-review

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes shell commands including git and gh to manage repository state, create worktrees, and interact with the GitHub API.
  • [REMOTE_CODE_EXECUTION]: The skill executes the project's own quality pipeline (e.g., composer fix, pest, tsc) to establish a green baseline for reviews. This involves executing code within the pull request but is a core functional requirement of the review process and is restricted to a temporary workspace.
  • [PROMPT_INJECTION]: The skill ingests external content from pull request metadata and comments. It mitigates potential risks through strict sub-agent task scoping and requiring explicit user approval before performing any external write operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 04:13 AM
Security Audit — agent-trust-hub — pr-review