principle-prove-it-works
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to verify work by reading artifacts like file contents and diffs, which acts as a data ingestion surface for potential indirect instructions.
- Ingestion points: In 'SKILL.md', the agent is told to read the 'real artifact' and 'actual value'.
- Boundary markers: No specific delimiters or safety instructions are provided for these ingestion points.
- Capability inventory: The agent is assumed to have the ability to read files and execute scripts.
- Sanitization: No sanitization is mentioned for the artifact content.
- [DYNAMIC_EXECUTION]: The skill encourages the agent to generate and run scripts at runtime to verify task completion.
- Evidence: The section 'Script the check when you can' in 'SKILL.md' instructs the agent to 'Write the script, run it'.
Audit Metadata