bmad-create-epics-and-stories

Pass

Audited by Gen Agent Trust Hub on Apr 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local Python script located at {project-root}/_bmad/scripts/resolve_customization.py during activation and completion to handle configuration merging and final tasks. This is standard functionality for the BMad framework and is restricted to the local project context.\n- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it ingests and processes content from external, untrusted project documents (PRDs, Architecture, and UX Design files).\n
  • Ingestion points: Reads requirements from markdown files located in the project's documentation directories.\n
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the workflow.\n
  • Capability inventory: The agent has the capability to write files (epics.md) and execute local Python commands.\n
  • Sanitization: The skill does not perform sanitization or validation of the text extracted from input documents before processing it.\n- [COMMAND_EXECUTION]: The workflow includes a dynamic execution mechanism where the workflow.on_complete configuration and activation_steps arrays are resolved and followed as instructions. While this allows for dynamic behavior, it relies on local configuration files provided by the user.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 27, 2026, 12:51 AM
Security Audit — agent-trust-hub — bmad-create-epics-and-stories