bmad-help
Pass
Audited by Gen Agent Trust Hub on May 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches module documentation (e.g., llms.txt) from remote URLs or local paths specified in the _bmad/_config/bmad-help.csv configuration file to answer user questions about specific modules.
- [PROMPT_INJECTION]: The skill processes untrusted data from local CSV files and remote documentation URLs to generate responses and recommend actions, which creates a surface for indirect prompt injection.
- Ingestion points: Data enters the agent context from the bmad-help.csv file and remote URLs specified within it.
- Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are used when processing this data.
- Capability inventory: The skill can recommend and offer to execute other BMad skills based on the identified workflow state.
- Sanitization: No sanitization or validation of the fetched external documentation content is specified.
Audit Metadata