design-patterns
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary functionality involves the ingestion and analysis of external source code, creating an attack surface for indirect prompt injection.
- Ingestion points: The 'Code Review' mode in
SKILL.mdexplicitly directs the agent to analyze, audit, and critique code provided by the user. - Boundary markers: The instruction set lacks explicit delimiters or instructions for the agent to ignore potentially malicious directions embedded within the code it is tasked to review.
- Capability inventory: The agent is authorized to generate complex code and provide design recommendations based on its analysis of untrusted inputs.
- Sanitization: There is no evidence of sanitization, filtering, or escaping logic applied to the user-provided code blocks prior to analysis.
Audit Metadata