bmad-project-context
Warn
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: MEDIUMDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [DYNAMIC_EXECUTION]: The skill executes Python scripts located at {project-root}/_bmad/scripts/resolve_customization.py and {project-root}/_bmad/scripts/resolve_config.py using the uv run command during its activation sequence. It also allows for the execution of arbitrary commands defined in the activation_steps_prepend and activation_steps_append fields of the customization configuration file found in the workspace.- [INDIRECT_PROMPT_INJECTION]: The skill has a broad ingestion surface, reading files like AGENTS.md, package.json, and documentation to synthesize instructions. Evidence Chain: (1) Ingestion points: AGENTS.md, manifests, and docs; (2) Boundary markers: Absent for ingestion; (3) Capability inventory: uv run (subprocess) and file-writing; (4) Sanitization: None identified for interpolated content.- [COMMAND_EXECUTION]: The skill utilizes shell commands to interact with the local environment, including uv run for script execution and git log for verifying historical changes in the repository.
Audit Metadata