prototype-question
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill documents its origins by citing public GitHub repositories from known developers and services (Matt Pocock and Cursor). These references are for attribution and do not involve the automated downloading or execution of untrusted remote code.
- [DYNAMIC_EXECUTION]: The skill's primary function is to generate and run 'throwaway' or 'disposable' code (probes) to answer technical questions. It mitigates associated risks by instructing the agent to isolate these artifacts, label them clearly as prototypes, and avoid using production-grade abstractions or persistence unless specifically required.
- [INDIRECT_PROMPT_INJECTION]: The skill operates on design questions provided in the agent's context. While this is an ingestion point for external data, the skill includes explicit constraints and 'planning-contract' approval boundaries to manage how generated code is handled and reported.
Audit Metadata