bmad-os-diataxis
Pass
Audited by Gen Agent Trust Hub on Apr 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's operations are limited to documentation files and are consistent with its stated purpose. It does not perform network operations or access system-level configuration.\n- [DATA_EXPOSURE_AND_EXFILTRATION]: The skill accesses documentation files within the project (e.g.,
docs/_STYLE_GUIDE.md). This access is localized and intended for its function, with no evidence of sensitive data harvesting or external data transmission.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes content from user-controlled files, which is an inherent surface for indirect prompt injection.\n - Ingestion points: Reads
docs/_STYLE_GUIDE.mdand user-specified target files as part of its doc editing flow.\n - Boundary markers: No specific delimiters are used when passing file content to subagents.\n
- Capability inventory: The agent uses an
Edit toolfor file modifications.\n - Sanitization: No explicit sanitization or validation of the ingested document content is performed.
Audit Metadata