Discover the pull requests this Paperclip instance opened (never community contributions), report what each is for and how confident we are that it is merge-ready, and automatically drive the non-ready ones back to green with /prepare-paperclip-pr — without ever merging.
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 required Stage B readiness run reads PR titles and bodies from GitHub (`gh pr view ... body`) on every candidate with no per-item selection, and GitHub issue/PR reading is medium under the rubric, even though the author allowlist limits candidates to this instance's own PRs.
paperclipai/paperclip
41a3520
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.