prototype
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill allows the agent to generate runnable prototypes (HTML, JS, TSX) based on user prompts. This ingestion of untrusted data into a code-generation workflow without explicit sanitization instructions creates a potential surface for indirect prompt injection or cross-site scripting (XSS) within the prototype environment.
- Ingestion points: User prompts are processed to define logic and UI in SKILL.md.
- Boundary markers: No specific delimiters or instructions to ignore embedded commands are provided for the generated code.
- Capability inventory: The skill involves file system writes, route modifications, and command execution through task runners like pnpm, python, and bun.
- Sanitization: No sanitization or escaping of user-provided data is mandated in the prototype generation process.
Audit Metadata