gds-create-epics-and-stories

Pass

Audited by Gen Agent Trust Hub on Jul 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local Python script {project-root}/_bmad/scripts/resolve_customization.py during the activation and completion phases to handle configuration merging.
  • [COMMAND_EXECUTION]: The workflow allows for arbitrary command execution via the on_complete configuration key defined in customize.toml, which is resolved and executed at the end of Step 4.
  • [PROMPT_INJECTION]: The workflow involves reading and extracting requirements from external files such as GDD.md, Architecture.md, and UX Design.md which may contain untrusted content.
  • Ingestion points: Files matching patterns like *gdd*.md, *architecture*.md, and *ux*.md are read in step-01-validate-prerequisites.md.
  • Boundary markers: The instructions do not define clear boundary markers or instructions to treat ingested content as data only, which could lead the agent to follow instructions embedded in those files.
  • Capability inventory: The skill has the ability to write to the local filesystem (epics.md) and execute project-local Python scripts.
  • Sanitization: There is no evidence of sanitization or filtering applied to the text extracted from the input documents.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 7, 2026, 06:20 PM
Security Audit — agent-trust-hub — gds-create-epics-and-stories