go-idiomatic-api-design
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions guide an AI agent to analyze and review user-supplied Go source code and API definitions. This introduces a surface where malicious instructions embedded in the analyzed data could potentially influence the agent's output. However, the skill lacks executable code or tools that would facilitate a high-impact exploit.
- Ingestion points: User-provided Go source files and package interfaces processed by the agent during the API review workflow (established in
workflows/review-public-api.md). - Boundary markers: The instructions do not define specific delimiters or encapsulation for the user-provided content.
- Capability inventory: The skill is composed entirely of markdown guidelines and YAML configuration. It does not define or use any subprocess calls, file-system write operations, or network tools beyond referencing documentation URLs.
- Sanitization: No specific sanitization or filtering of the input source code is defined in the skill logic.
Audit Metadata