bmad-bmb-setup
Pass
Audited by Gen Agent Trust Hub on Mar 31, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Executes local Python scripts ('merge-config.py', 'merge-help-csv.py', 'cleanup-legacy.py') to modify project configuration and perform filesystem cleanup. The 'cleanup-legacy.py' script utilizes 'shutil.rmtree' to remove legacy directory trees, which is a powerful operation. While the skill includes logic to verify that skills are installed before deletion, the execution of shell commands based on internal logic constitutes a significant capability.
- [PROMPT_INJECTION]: Identifies an indirect prompt injection surface in the way user-provided configuration is utilized. Ingestion points: User input collected for 'user_name' and 'communication_language' via the 'Collect Configuration' section in 'SKILL.md'. Boundary markers: Absent. Capability inventory: The agent is explicitly instructed to use these values (e.g., addressing the user by name) for the remainder of the session, effectively injecting unvalidated data into future prompts. Sanitization: Absent.
Audit Metadata