issue
Work a single GitHub issue end to end — fetch its full context, branch, and start. Use when Josh points at an issue and wants it worked: 'let's look at issue 43', 'work on #43', 'start 43', 'pick up foo/bar#43', 'what's next?', 'grab the next issue', 'let's fix that bug'. Also use with no ref when he says 'let's get started' or 'what am I on?' — the ref resolves from the conversation or from the current git branch. Routing: if the issue has at least one open sub-issue it is a parent, so hand off to the `epic` skill with that ref; `epic` covers 'close out the epic', 'work through all of #40's children', 'do the whole epic'.
94%
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
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
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.
Why it was flagged
The required workflow fetches and processes GitHub issue bodies, comments, and metadata via CLI commands (`gh issue view`, `gh api`), which exposes the agent to outsider-authored free text.
- Repository
joshmanders/dotfiles
- Revision
92186fe
- Audited
- Security analysis
Is this your skill?
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.