bmad-os-release-module
Pass
Audited by Gen Agent Trust Hub on Feb 22, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION] (SAFE): The skill executes
npm version,npm publish,git push, andgh releasecommands. While these are powerful commands, they are strictly necessary for the skill's primary stated purpose of automating software releases. The instructions include a requirement to wait for user confirmation before destructive operations, which serves as a significant safety control. - [DATA_EXFILTRATION] (SAFE): The skill pushes code to GitHub and publishes packages to npm. These are standard operations for a release tool and target well-known, trusted platforms (GitHub and npm) rather than suspicious third-party servers.
- [INDIRECT_PROMPT_INJECTION] (LOW): The skill ingests user-provided changelog entries (Step 2) and incorporates them into the release process. While this is a potential ingestion point for instructions, the risk is mitigated by the 'Confirmation' step (Step 3) where the model is required to show the proposed changes to the user before proceeding.
Audit Metadata