pragmatic-code-review
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data in the form of code diffs and OpenSpec artifacts, creating a surface for indirect prompt injection attacks where malicious instructions could be embedded in the code to influence the agent's behavior.
- Ingestion points: The agent reads user-provided code changes and files located in the openspec/ directory.
- Boundary markers: The instructions do not specify explicit delimiters or warnings for the agent to ignore instructions embedded within the code being reviewed.
- Capability inventory: The skill instructions explicitly restrict the agent from using file modification tools such as Edit or Write during the review, though the underlying agent environment may still possess these capabilities.
- Sanitization: No explicit sanitization or filtering of the code content is mentioned before processing.
Audit Metadata