principle-prove-it-works
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions advise the agent to verify task outputs by inspecting real artifacts, such as file contents, git diffs, and runtime behavior. This establishes an ingestion point for untrusted data that could potentially contain malicious instructions intended to influence the agent's context during the verification phase.
- [DYNAMIC_EXECUTION]: The skill encourages the agent to create and run deterministic scripts to compare outputs and prove correctness. This involves the generation and execution of code at runtime, which is a common pattern for automated verification and testing workflows.
Audit Metadata