gds-dev-story

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 at {project-root}/_bmad/scripts/resolve_customization.py to handle configuration merging from team and user-level override files. This script is part of the vendor's framework.
  • [COMMAND_EXECUTION]: Utilizes git rev-parse HEAD to capture the current version control state for progress tracking in the story metadata.
  • [PROMPT_INJECTION]: The skill ingests and processes 'story' files and 'sprint-status' documents which represent an indirect prompt injection surface. The agent uses the content of these files to determine its implementation steps and code changes.
  • Ingestion points: Reads sprint-status.yaml, project-context.md, and dynamically discovered story markdown files (e.g., 1-2-user-auth.md).
  • Boundary markers: The instructions use XML-like <step> and <workflow> tags to separate the agent's logic from the data it processes.
  • Capability inventory: The skill is capable of executing shell commands (Python and Git), writing to the local filesystem (updating story files), and creating/running tests.
  • Sanitization: The workflow incorporates a comprehensive 'Definition of Done' checklist and regression test requirements to verify that the agent's output matches the specified requirements and does not introduce unintended behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 7, 2026, 06:21 PM
Security Audit — agent-trust-hub — gds-dev-story