gds-create-narrative

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute a Python script located at {project-root}/_bmad/scripts/resolve_customization.py during initialization and at the end of the workflow. This script is part of the vendor's internal framework for resolving configuration and completion hooks.
  • [DATA_EXPOSURE]: The workflow reads from several local project files, including _bmad/gds/config.yaml, project-context.md, and existing game design documents. This access is limited to the user's project directory and is necessary for providing context-aware narrative assistance.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from project files which could potentially contain malicious instructions.
  • Ingestion points: {project-root}/_bmad/gds/config.yaml and {project-root}/**/project-context.md (via customize.toml).
  • Boundary markers: Content is loaded as foundational facts or used to populate document templates.
  • Capability inventory: File system read/write access and local command execution via Python.
  • Sanitization: No explicit sanitization or filtering of the ingested project content is mentioned in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 08:56 AM
Security Audit — agent-trust-hub — gds-create-narrative