cub-mutate
Change data inside an existing ConfigHub Unit, preferring a function over a hand-edit, and write it so it still works in every variant. Use for "update the image", "bump the replicas", "set the annotation", "apply defaults", a bulk edit, or "why did that change miss some variants?". Not for creating a Unit (kubernetes-resources).
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
The cub-mutate runtime workflow ingests outsider-authored free text via the user’s natural-language prompt (and derived arguments like space/unit selectors and change intent), which the agent then uses to compose cub function/set commands without any indication of hard separation from the workflow’s decision-making.
- 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.