Use when preparing or executing a release - verifies changelog content, updates version references, commits release prep, and, when the maintainer explicitly asks, pushes the release tag that triggers automation
67
81%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The workflow uses `git log`/`git diff` to build free-form text that includes commit messages and changes, then feeds it into an LLM via the runtime command `gemini ... "Analyze these git changes ... $(git log ...) $(git diff ...)"`; those commit messages/PR authorship are outsider-authored content introduced through the repo history (not chosen by the operator in this skill).
a8b696d
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.