bmad-agent-pm
Pass
Audited by Gen Agent Trust Hub on Nov 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local Python scripts using
uv runto resolve project-specific customizations, configurations, and to list available templates. These scripts are located within the user's project structure under the_bmad/directory. uv run {project-root}/_bmad/scripts/resolve_customization.pyuv run {project-root}/_bmad/scripts/resolve_config.pyuv run {project-root}/_bmad/scripts/list_templates.pyuv run {project-root}/_bmad/method/scripts/tickets.py- [EXTERNAL_DOWNLOADS]: The skill provides instructions for the agent to suggest installing the core
bmadskill from the vendor's official GitHub repository if the environment setup is incomplete. npx skills add bmad-code-org/BMAD-METHOD --skill bmad- [INDIRECT_PROMPT_INJECTION]: The skill processes external project files and user-provided inputs to generate structured planning documents, representing an indirect injection attack surface.
- Ingestion points: The skill reads
persistent_factsfrom files or globs within the project root and parses content from initiative or epic tickets. - Boundary markers: No explicit boundary markers or delimiters for untrusted content are defined in the instructions; the skill relies on the downstream
bmad-facilitateskill for content processing. - Capability inventory: The skill has capabilities to execute local scripts and invoke external skills.
- Sanitization: No explicit sanitization or validation of the processed data is performed within this skill's instructions.
Audit Metadata