gds-create-epics-and-stories

Pass

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a Python script located at {project-root}/_bmad/scripts/resolve_customization.py during the activation and completion phases to handle configuration merging and workflow finalization.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes content from external project documents to extract functional and non-functional requirements, creating an attack surface where malicious instructions in those documents could influence the agent's behavior.
  • Ingestion points: The skill reads from GDD.md, Architecture.md, and UX Design.md files (or their sharded versions) located within the {planning_artifacts} directory.
  • Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore or isolate embedded instructions within the ingested requirement documents.
  • Capability inventory: The skill is capable of writing to the file system ({planning_artifacts}/epics.md) and executing shell commands via python3 as defined in the activation and completion steps.
  • Sanitization: No explicit sanitization, validation, or filtering of the content extracted from the input documents is described before it is processed or saved.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 5, 2026, 08:01 PM
Security Audit — agent-trust-hub — gds-create-epics-and-stories