eg-constructive-code-review
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze and respond to untrusted external data, specifically code diffs and pull requests provided by the user.
- Ingestion points: Pull request content, patches, and diffs (referenced in SKILL.md).
- Boundary markers: The instructions do not define specific delimiters or warnings to ignore instructions embedded within the code being reviewed.
- Capability inventory: No technical capabilities such as subprocess execution, file writing, or network requests are present in this skill.
- Sanitization: There are no instructions for sanitizing or escaping the user-provided code content before processing.
Audit Metadata