prototype
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user prompts and existing code to generate executable logic, forming a surface for potential indirect prompt injection.\n
- Ingestion points: The skill takes input from the "user's prompt" and "surrounding code" to define the prototype's logic (SKILL.md).\n
- Boundary markers: No delimiters or safety instructions are defined to isolate user input within the generated code.\n
- Capability inventory: The skill produces a single HTML file containing a functional JavaScript module for local execution (LOGIC.md).\n
- Sanitization: There are no explicit instructions for sanitizing or escaping user data before it is embedded in the generated HTML/JS code.\n- [DYNAMIC_EXECUTION]: The skill involves the generation of JavaScript code for execution in a browser environment.\n
- Evidence: LOGIC.md instructs the agent to create a portable JavaScript logic module and build a shareable HTML file that anyone can run by double-clicking.
Audit Metadata