spec
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE] (SAFE): No malicious code or behavior detected. The skill's logic is confined to information gathering and documentation generation.
- [Indirect Prompt Injection] (SAFE): The skill contains a vulnerability surface for indirect prompt injection as it processes untrusted user input ($1) into a document. 1. Ingestion points: User-provided functional descriptions in the $1 argument. 2. Boundary markers: Absent. 3. Capability inventory: The skill writes a SPEC.md file to the project root. 4. Sanitization: No sanitization is performed on user input, but the risk is assessed as negligible because the output is static markdown intended for documentation and does not invoke executable commands.
Audit Metadata