do-architecture-md
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill contains a documentation generation surface that processes untrusted project files. This is documented as a standard risk factor for indirect prompt injection but is classified as safe as it is the primary purpose of the utility.
- Ingestion points: SKILL.md Step 1 instructions to read README and project config files.
- Boundary markers: None.
- Capability inventory: tree, glob, and read tools used for codebase exploration.
- Sanitization: None.
- [SAFE]: No malicious patterns, credentials, or dangerous command executions were detected. The skill references legitimate developer resources and follows standard practices.
Audit Metadata