bmad-agent-analyst
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local Python scripts (
resolve_customization.py,resolve_config.py) viauv runto merge configuration files and resolve persona settings at runtime. These scripts are located within the project's internal_bmad/scriptsdirectory. - [INDIRECT_PROMPT_INJECTION]: The skill features a data ingestion surface through the
persistent_factsconfiguration, which can load content from local files (e.g., viafile:prefixes). This is used to provide the agent with foundational project context. - [EXTERNAL_DOWNLOADS]: The
module-manifest.tomlidentifies an update source pointing to the vendor's official GitHub repository (bmad-code-org/bmad-skills). This is standard for managing skill updates and does not involve runtime execution of untrusted remote code.
Audit Metadata