branch-review-before-pr

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or security risks were identified. The skill follows best practice guidelines for a code review tool, including requiring user confirmation before any modifications and restricting its scope to the provided git diff based on a predefined checklist.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted code diffs which may contain embedded instructions. While this is an inherent risk for code review tools, the skill provides a strict instructional framework for the agent.\n
  • Ingestion points: Reads git diff output using the Bash tool and reads the checklist.md file.\n
  • Boundary markers: No explicit delimiters (e.g., XML tags) are specified in the instructions to separate the untrusted diff content from the agent's primary instructions.\n
  • Capability inventory: Uses Bash, Read, Write, Edit, and AskUserQuestion tools. The capability to edit code is gated by mandatory user approval.\n
  • Sanitization: No specific sanitization or filtering of the code diff content is described before the agent processes it for the review.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 06:56 PM
Security Audit — agent-trust-hub — branch-review-before-pr