ln-63-release-publisher
Pass
Audited by Gen Agent Trust Hub on Jul 20, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted external data, such as commit messages and repository manifests, to generate release documentation.
- Ingestion points: Git commit bodies, branch history, manifest files, and user-facing migration notes.
- Boundary markers: The skill explicitly requires a human-in-the-loop approval step for the exact tag, title, and notes before any publication occurs.
- Capability inventory: The agent utilizes
gitandgh(GitHub CLI) for repository operations. - Sanitization: The instructions mandate writing release notes to a temporary file rather than passing strings directly to shell commands, preventing command injection from markdown content.
- [DATA_EXFILTRATION]: The skill interacts with the repository host (GitHub) for its primary purpose. It includes specific instructions to use secure host credential stores and explicitly forbids echoing secrets in the logs or output.
- [COMMAND_EXECUTION]: The skill uses Git and GitHub CLI for release management. Security is maintained by requiring explicit user approval for planned commands and using isolated verification steps for installation instructions.
Audit Metadata