codeaudit
Pass
Audited by Gen Agent Trust Hub on Nov 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's core function is to process untrusted source code from external repositories or user uploads, which is a vector for indirect prompt injection attacks.
- Ingestion points: Auditing of third-party plugins, applications, and repositories provided or fetched by the operator as specified in SKILL.md.
- Boundary markers: The methodology does not include instructions for the agent to use delimiters or specific ignore-previous-instruction warnings when ingesting code files.
- Capability inventory: The skill requires the agent to have file system access (reading source code, writing artifacts) and suggests the ability to execute commands (e.g., via docker-compose) for Proof of Concept (PoC) verification.
- Sanitization: The instructions do not define any sanitization or filtering requirements for the code content prior to analysis or execution in a PoC environment.
Audit Metadata