principle-prove-it-works
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of instructional text guiding the agent on how to verify its work. No malicious patterns were detected.
- [DYNAMIC_EXECUTION]: The skill encourages the agent to write and execute scripts for verification purposes ('Write the script, run it'). This is a core feature of the skill intended for confirming task correctness and is acceptable within its functional context.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and verify external data and system states, which represents a potential surface for indirect prompt injection if the artifacts being inspected are controlled by an attacker.
- Ingestion points: Artifacts, file contents, and process state (SKILL.md).
- Boundary markers: None present.
- Capability inventory: Script execution and file reading (SKILL.md).
- Sanitization: No explicit sanitization of the artifacts is mentioned.
Audit Metadata