document-architecture
Pass
Audited by Gen Agent Trust Hub on Jul 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is instructional and documentation-oriented, containing no executable code or network requests.
- [PROMPT_INJECTION]: The skill involves reading repository files to gather architectural evidence, creating a surface for indirect prompt injection. Ingestion points: Repository manifests, source code, AGENTS.md, and configuration files; Boundary markers: Not specified; Capability inventory: Architecture documentation; Sanitization: None.
Audit Metadata