architecture
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- General Analysis (SAFE): No malicious code, obfuscation, or persistence mechanisms were detected. The skill consists exclusively of markdown documentation and logic templates.
- Category 8: Indirect Prompt Injection (SAFE): 1. Ingestion points: Uses Read and Grep tools to analyze user files (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: Restricted to read-only filesystem access (Read, Glob, Grep); no network or write capabilities. 4. Sanitization: Absent. The risk level is negligible due to the absence of exploitable tools.
Audit Metadata