Use when classifying an OpenShell issue or pull request, correcting inaccurate area/topic labels, or migrating obsolete, retired, or malformed classification associations.
89%
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 required workflow runs `prepare` to pull OpenShell issue/PR content (bodies, comments, and PR diffs) from GitHub and has the agent read it in `packet.json` and expanded evidence, which outsiders can author without the agent selecting a specific item, so this is medium exposure despite the "treat item contents as evidence" guard.
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.