Plan and implement work described in a GitHub issue, including verification, documentation, and a PR that closes the issue.
81%
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 reads GitHub issues, comments, and linked PR descriptions via the `gh issue view` command, exposing the agent to outsider-authored free text.
NVIDIA/OpenShell
2e5589b
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.