bmod-core-tools

Pass

Audited by Gen Agent Trust Hub on Sep 22, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions and configuration for fetching updates and additional components from the vendor's repository on GitHub (bmad-code-org/BMAD-METHOD).
  • [INDIRECT_PROMPT_INJECTION]: The module describes research workflows that ingest data from external web searches and user-provided notes to generate summaries or personas.
  • Ingestion points: External web content processed by bmad-deep-recon, user-supplied notes in bmad-party-mode, and local TOML configuration files.
  • Boundary markers: The documentation does not specify explicit delimiters for external content within these files.
  • Capability inventory: Installation commands (npx) and configuration resolution scripts (python).
  • Sanitization: Documentation indicates that research results are presented as cited summaries, implying a degree of summarization/filtering.
  • [DYNAMIC_EXECUTION]: The configuration system utilizes internal Python scripts (resolve_customization.py and resolve_config.py) to resolve and merge settings from various local TOML files at runtime.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 22, 2026, 11:05 AM
Security Audit — agent-trust-hub — bmod-core-tools