ps-principle-prove-it-works
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides high-level principles for verifying work by checking actual artifacts rather than relying on self-reports. No malicious patterns such as credential theft, obfuscation, or unauthorized network activity were detected.\n- [INDIRECT_PROMPT_INJECTION]: The skill establishes a workflow where the agent ingests external data (artifacts) for verification, which represents a standard indirect prompt injection surface.\n
- Ingestion points: SKILL.md instructs the agent to read real artifacts, actual values, git diffs, and file contents.\n
- Boundary markers: No explicit markers or instructions to ignore embedded prompts within the artifacts are provided.\n
- Capability inventory: The skill leverages capabilities to build projects, execute features, read the filesystem, and write/run deterministic check scripts.\n
- Sanitization: No instructions for sanitizing or escaping content from the artifacts are included.
Audit Metadata