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