verify-apply
Verify a published ConfigHub Space Release, then prove controller and cluster convergence read-only. Use after release-publish or for "did it deploy?", "is it live?", "did Argo pick it up?", and release close-out.
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 SKILL.md describes a read-only runtime workflow that ingests outsider-authored free text from the user as natural-language prompts to drive specific, provider-authenticated lookups (cub release/revision/space, Argo/Flux, and kubectl), rather than passively ingesting external feeds/queues/items posted by outsiders without selecting identities.
- 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.