bmad-auto-resolve

Pass

Audited by Gen Agent Trust Hub on Jun 24, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's primary function is to manage an interactive escalation-resolution workflow within a local development environment. It focuses on mediating between automated processes and human decision-making.
  • [COMMAND_EXECUTION]: The skill relies on specific environment variables ($BMAD_AUTO_RUN_DIR, $BMAD_AUTO_STORY_KEY, $BMAD_AUTO_RESOLVE_CONTEXT) to locate files. It does not invoke arbitrary shell commands or interact with the operating system outside of its defined scope.
  • [DATA_EXPOSURE]: File access is limited to project-specific markdown and JSON files. The skill does not access sensitive system directories, credentials, or environment variables containing secrets.
  • [PROMPT_INJECTION]: The instructions establish a clear identity and I/O contract for the agent. While it includes directives like "MUST NOT", these are operational constraints for the workflow rather than attempts to bypass security guardrails.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 24, 2026, 08:16 AM
Security Audit — agent-trust-hub — bmad-auto-resolve