wds-1-project-brief
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized execution vectors were detected within the skill files or templates. The skill's behavior is consistent with its stated purpose of project documentation and facilitation.
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection because it ingests untrusted user input during discovery workshops (e.g., vision capture, user definition) and interpolates this data into markdown templates. This risk is classified as low because the agent is instructed to 'synthesize' the input rather than repeat it verbatim, and the output is stored as static documentation files on the local filesystem rather than being used for downstream automated execution.
- [DATA_EXPOSURE]: The skill reads from and writes to the local project directory (e.g.,
_bmad/wds/config.yaml,_progress/00-design-log.md). This activity is restricted to the project's own folder and constitutes standard operational behavior for a documentation and state-tracking tool.
Audit Metadata