flux-opencode-release
Pass
Audited by Gen Agent Trust Hub on Jul 31, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's operations, including manifest updates and repository tagging, are entirely consistent with its stated purpose and exhibit no malicious patterns.
- [COMMAND_EXECUTION]: The skill utilizes git for committing changes and pushing tags. These commands are essential for the release process and are scoped to the project's local environment and remote origin.
- [PROMPT_INJECTION]: The skill ingests pull request descriptions to generate narrative release notes, which is a standard surface for indirect prompt injection. 1. Ingestion points: Merged PR descriptions accessed in Step 5. 2. Boundary markers: Not explicitly defined. 3. Capability inventory: Git push, git commit, and local file modifications. 4. Sanitization: The instructions mandate that generated narrative notes must be sanity-checked by the user.
Audit Metadata