unopim-code-review
Pass
Audited by Gen Agent Trust Hub on Jul 31, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data in the form of code diffs and pull requests for the UnoPim project. This creates a potential surface for indirect prompt injection where an attacker could embed malicious instructions within the code being reviewed to influence the agent's behavior.
- Ingestion points: The skill processes code changes and pull request content provided to the agent as input (SKILL.md).
- Boundary markers: The instructions do not define explicit delimiters or 'ignore embedded instructions' markers for the code content being analyzed.
- Capability inventory: The skill appears to be limited to providing textual analysis and reviews; no file-write, network operations, or shell execution capabilities were detected within the skill's own instructions.
- Sanitization: There are no instructions for the agent to sanitize or escape the content of the diffs before processing them.
Audit Metadata