principle-prove-it-works
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill encourages the agent to verify work by directly inspecting external artifacts such as git diffs, file contents, and runtime behavior. These ingestion points represent a surface where untrusted data could contain embedded instructions to influence the agent.
- Ingestion points: Git diffs, file contents, and runtime behavior output (SKILL.md).
- Boundary markers: The instructions do not specify the use of delimiters or warnings to ignore instructions embedded in the artifacts.
- Capability inventory: The skill assumes the agent has capabilities for file system access and script execution to perform verification.
- Sanitization: No mention of sanitizing or escaping content from external artifacts before processing.
- [DYNAMIC_EXECUTION]: The instructions recommend that the agent 'script the check' by writing and running deterministic scripts to verify task correctness. This involves the generation and execution of code at runtime based on the context of the work being verified.
Audit Metadata