bmad-dev-auto

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes content from external configuration files which could contain malicious instructions designed to influence agent behavior during the migration process.
  • Ingestion points: Reads local TOML files located at {project-root}/_bmad/custom/.
  • Boundary markers: Absent; there are no specific markers or instructions provided to the agent to treat the file content as untrusted data.
  • Capability inventory: The skill has the ability to read, write, and rename files within the project structure, and can invoke the successor skill bmad-build-auto.
  • Sanitization: No formal validation or escaping of the TOML content is specified before the agent interprets the data.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 06:12 PM
Security Audit — agent-trust-hub — bmad-dev-auto