architecture
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- [SAFE] (SAFE): No malicious patterns, obfuscation, or unauthorized access attempts were found. The skill instructions are purely structural and focus on best practices for software architecture.
- [PROMPT_INJECTION] (LOW): The skill exhibits an indirect prompt injection surface as it is designed to process untrusted data from local files using the
Read,Glob, andGreptools. However, the risk is negligible (Tier: LOW/INFO) because the skill lacks any tools for data exfiltration, file modification, or system execution. Evidence: Data enters via Read/Glob/Grep (SKILL.md), no explicit boundary markers are defined, capability inventory is limited to read-only tools, and no sanitization of read content is performed.
Audit Metadata