prototype
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill follows secure design principles for prototyping, specifically recommending that prototype code be kept separate from production code, use in-memory storage instead of persistent databases, and be easily removable once the prototype's purpose is served.\n- [SAFE]: The guidelines rely on the project's existing task runners (e.g., pnpm, python, bun) and warn against introducing new package managers or runtimes for prototypes, minimizing supply chain risks.\n- [INDIRECT_PROMPT_INJECTION]: The skill facilitates code generation based on user prompts, which is an inherent part of its prototyping functionality. \n
- Ingestion points: User prompts are used to determine the prototype branch and logic (SKILL.md, LOGIC.md). \n
- Boundary markers: The skill does not define specific prompt delimiters or instructions to ignore embedded commands. \n
- Capability inventory: The skill utilizes file-writing for prototype creation and command execution via existing project task runners. \n
- Sanitization: The instructions mitigate risk by mandating that logic be isolated in pure, portable modules separated from I/O shells.
Audit Metadata