release
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a standard software release workflow, automating tasks such as versioning, changelog generation, and tagging for the 'es-toolkit' project.
- [COMMAND_EXECUTION]: The skill uses the Bash tool to run Git and GitHub CLI (
gh) commands. These operations are restricted to project management tasks within thetoss/es-toolkitrepository, which aligns with the provided author context. - [PROMPT_INJECTION]: The skill contains explicit instructions to the agent to never auto-approve sensitive actions and to wait for genuine user input. These directives serve as safety guardrails rather than malicious attempts to override system behavior.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data in the form of Git commit messages and GitHub usernames to generate the changelog. However, the attack surface is limited as the output is formatted as Markdown text for a changelog entry, and the workflow includes a mandatory preview and confirmation step where the user reviews all changes before they are applied or pushed.
Audit Metadata