code-review-guide
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of Markdown instructions and quality guidelines. It does not include any scripts, configuration files, or external tool definitions that could execute commands or access the file system.
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and analyze untrusted external data in the form of code diffs and pull requests. While this creates a potential surface for indirect prompt injection (e.g., instructions hidden in comments within the code being reviewed), the risk is negligible as the skill lacks any capabilities for network exfiltration, file modification, or system command execution. Any such injection would only be able to influence the text of the review output itself.
- Ingestion points: Untrusted data enters via 'The change' (diff/PR) and 'Context' inputs as defined in
SKILL.md. - Boundary markers: Absent; there are no specific delimiters or warnings instructed to the agent to disregard instructions within the processed code.
- Capability inventory: None; the skill does not request any tools, subprocesses, or file-write permissions.
- Sanitization: Absent; the skill does not include instructions for sanitizing or escaping the provided code before analysis.
Audit Metadata