code-pr-review
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or suspicious instructions were detected in the skill's code or configuration.- [EXTERNAL_DOWNLOADS]: The skill utilizes external data by fetching pull request content from services like GitHub and GitLab using tool-based network requests. This is standard functionality for the intended use case.- [PROMPT_INJECTION]: The skill processes untrusted external content (code diffs and PR descriptions), which presents a potential surface for indirect prompt injection.
- Ingestion points: Raw git diffs, PR URLs, and uploaded files as defined in SKILL.md.
- Boundary markers: The instructions do not specify explicit delimiters or markers to separate untrusted user input from the agent's instructions.
- Capability inventory: The skill uses network reading capabilities (web_fetch) but does not request file writing or command execution permissions.
- Sanitization: There are no instructions for sanitizing or escaping the content of the pull requests before the agent processes them.
Audit Metadata