Draft and review Epicenter pull request titles and bodies, including changelog and merge details. Use when creating a PR or editing its text, not for local commits, branches, or issue replies.
68
85%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
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 instructs the agent to read GitHub issues and comments using `gh issue view` and `gh issue list`, which allows outsiders to inject untrusted free text into the agent's context.
f9441c8
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.