bmad-create-epics-and-stories

Pass

Audited by Gen Agent Trust Hub on May 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute a local Python script located at {project-root}/_bmad/scripts/resolve_customization.py to handle configuration merging and post-completion tasks. This script is part of the vendor's framework environment.\n- [PROMPT_INJECTION]: The skill processes content from untrusted external documents (PRD, Architecture, and UX Design files), which introduces an indirect prompt injection surface.\n
  • Ingestion points: PRD.md, Architecture.md, and UX Design.md (as described in step-01-validate-prerequisites.md).\n
  • Boundary markers: Absent; the files are read and processed without explicit delimiters or instructions to ignore nested prompts.\n
  • Capability inventory: File system write access (to create and update {planning_artifacts}/epics.md) and local command execution (python3).\n
  • Sanitization: None; the skill relies on the LLM to extract requirements from the raw text provided in input documents.
Audit Metadata
Risk Level
SAFE
Analyzed
May 10, 2026, 05:26 PM