bmad-product-brief
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local Python scripts (
resolve_customization.py,resolve_config.py,memlog.py) viauv runto manage customization and state.- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data which could contain malicious instructions. - Ingestion points: The
## Discoveryphase ingests memos, transcripts, and web research results. - Boundary markers: No explicit markers are used to separate user data from instructions.
- Capability inventory: The skill writes to the local filesystem and uses external MCP tools (Confluence, Slack).
- Sanitization: No sanitization is performed on input data.
Audit Metadata