prototype
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill consists entirely of instructional Markdown documentation and a YAML metadata file. It does not distribute any executable scripts or binary files.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to generate prototypes from user prompts and code context (ingestion points). It lacks specific instructions for boundary markers or sanitization within the generated code but mitigates risk by prescribing that prototypes be isolated, throwaway artifacts.
- [DYNAMIC_EXECUTION]: The workflow involves generating and running scripts via project task runners. This capability (file writing and execution) is restricted to local development context by the skill's instructions.
Audit Metadata