phoenix-code-review
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze external code, which constitutes untrusted input. This creates an attack surface for indirect prompt injection where malicious instructions could be embedded in the code files being reviewed. \n- Ingestion points: Phoenix source code (controllers, contexts, routers, and plugs) provided for review. \n- Boundary markers: The skill does not provide instructions for delimiters or warnings to ignore instructions within the reviewed code. \n- Capability inventory: The skill provides reasoning logic for the agent, which may use platform-level tools like the filesystem or shell to read and analyze the project. \n- Sanitization: No validation or sanitization of the input code is defined.
Audit Metadata