prototype
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to analyze user prompts and the surrounding codebase to generate functional logic or UI prototypes, creating a surface for indirect prompt injection.
- Ingestion points: User input (prompts) and surrounding codebase (modules, components) are used to determine prototype shape and logic (SKILL.md, LOGIC.md, UI.md).
- Boundary markers: The skill lacks explicit instructions or delimiters to isolate the agent from potentially malicious instructions embedded in the processed codebase.
- Capability inventory: The agent is authorized to write new code files (HTML, TSX, JS) and potentially interface with local scratch databases or files (SKILL.md).
- Sanitization: There are no instructions for sanitizing or validating the input data before it is interpolated into the prototype code.
Audit Metadata