bmad-architecture

Pass

Audited by Gen Agent Trust Hub on Nov 13, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONDYNAMIC_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external ticket files, existing architecture documents, and codebases, which are potential ingestion points for untrusted data.
  • Ingestion points: The agent reads ticket files (<type>-<slug>.md), architecture spines, and project source code to derive invariants.
  • Boundary markers: The skill employs a 'Reviewer Gate' (references/reviewer-gate.md) that uses parallel subagents to independently verify the spine against a rubric and adversarial lenses, preventing the agent from blindly following embedded instructions.
  • Capability inventory: The skill can write architecture documents and memlogs to the project workspace and produce human-facing HTML reports.
  • Sanitization: It requires user confirmation for Assumptions and Open Questions before artifacts are finalized.
  • [COMMAND_EXECUTION]: The skill executes utility scripts located within the project's _bmad/scripts directory to manage metadata and perform linting.
  • Evidence: Subprocess execution of scripts/memlog.py, scripts/resolve_customization.py, and scripts/lint_spine.py via uv run.
  • [DYNAMIC_EXECUTION]: The workflow allows for the execution of custom steps defined in the customize.toml configuration file.
  • Evidence: The skill executes workflow.activation_steps_prepend and workflow.activation_steps_append as part of its initialization sequence.
  • [EXTERNAL_DOWNLOADS]: The skill documentation suggests installing the core BMad method components from the vendor's official repository.
  • Evidence: Instructions include npx skills add bmad-code-org/BMAD-METHOD --skill bmad, which targets the author's own trusted organization resources.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 13, 2026, 10:20 PM