The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses a bash script fragment to verify the existence of 11 required reverse-engineering documents in the local directory. This is a standard check for prerequisites and does not perform dangerous operations.\n- [EXTERNAL_DOWNLOADS]: The documentation mentions the bmad-method package as a suggested manual installation step for the user via npx. This is a vendor-related resource and is not automatically downloaded or executed by the skill.\n- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it processes untrusted data from local markdown files. (1) Ingestion points: 11 files in docs/reverse-engineering/. (2) Boundary markers: Absent. (3) Capability inventory: File-write operations to _bmad-output/planning-artifacts/. (4) Sanitization: Absent. This risk is considered safe as the skill's logic is restricted to document transformation without high-risk execution capabilities.

bmad-synthesize