matt-prototype
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill instructions describe a workflow for creating isolated logic and UI prototypes using standard, well-known development tools and practices.
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the generation of code based on untrusted external inputs. (1) Ingestion points: user prompts and surrounding codebase. (2) Boundary markers: none specified. (3) Capability inventory: the agent can write prototype files and suggest shell commands. (4) Sanitization: the instructions do not specify a process for cleaning or validating external inputs before interpolation.
Audit Metadata