prototype
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user prompts and project code to generate executable logic and UI prototypes. The instructions explicitly prioritize speed over 'polish,' resulting in a lack of input sanitization or security guardrails in the generated artifacts.\n
- Ingestion points: User prompts and existing project context files (referenced in SKILL.md).\n
- Boundary markers: The skill does not define specific delimiters or instructions to prevent the generated code from obeying malicious instructions embedded in the input data.\n
- Capability inventory: The agent is instructed to create executable files (HTML, TSX, JS, Python) and provide commands for their execution using project task runners like pnpm, python, or bun.\n
- Sanitization: Explicitly omitted; the skill directs the agent to skip error handling and abstractions to favor rapid learning.\n- [DYNAMIC_EXECUTION]: The skill involves the generation of executable scripts and HTML components at runtime based on user requirements. While intended for rapid prototyping, the creation and suggested execution of these files (e.g., via 'python ' or 'bun ') constitutes dynamic code generation.
Audit Metadata