bmad-os-audit-file-refs
Pass
Audited by Gen Agent Trust Hub on Feb 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a shell command sequence involving
find,grep, andsortto generate a list of target files for the auditing process. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface through the ingestion of external file content.
- Ingestion points: The skill reads Markdown and YAML files from the
src/bmm,src/core, andsrc/utilitydirectories. - Boundary markers: No specific delimiters or boundary markers are used to separate the ingested file content from the subagent's core instructions.
- Capability inventory: The skill utilizes local shell execution, file system read access, and the ability to spawn and instruct subagents.
- Sanitization: File content is processed directly by subagents without prior sanitization or instruction-filtering.
Audit Metadata