MUST USE for ANY git operations: atomic commits, rebase/squash/fixup, and history search (blame, bisect, log -S, reflog). Load it before running git yourself, or pass load_skills=['git-master'] to the task that commits. Triggers: 'commit', 'rebase', 'squash', 'who wrote', 'when was X added', 'find the commit that'.
92%
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 conditional PR-evidence flow requires opening a target GitHub PR or issue page in an authenticated session to read its CSRF token and repository id, which exposes the agent to outsider-authored PR/issue text under the "any GitHub issue/PR reading" rule.
code-yeongyu/oh-my-openagent
687f5af
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.