rollback-revision
Roll back by moving one or more Unit heads to bound prior revisions via cub unit update --restore, then hand off to release-publish. Use for "roll back this change", "revert the last release", "undo the ChangeSet", or "restore to the last applied revision". Not for a clearer one-field forward fix.
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
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
Source text from outsider authors is supplied only via the user’s rollback request (e.g., the prompts in evals/evals.json), but the required runtime workflow described in SKILL.md performs rollback only after explicit, user-confirmed resolution of specific Unit/ChangeSet restore targets and does not describe ingesting arbitrary feed/queue content without selecting an item.
- Repository
- confighub/confighub-skills
- Commit
ba61249
- 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.