cub-query
Find, count, inspect, or audit Kubernetes config stored in ConfigHub — cub k8s get and cub resource list to browse resources, cub unit list for Units. Use for fleet sweeps and single-workload lookups; route "currently running/deployed" claims through verify-apply, because ConfigHub metadata alone is not runtime proof.
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
Skill `cub-query` ingest path is user-authored natural-language prompts that drive `cub unit list`/`cub resource list`/`cub k8s get`/`cub function get` filter parameters (`--where`, `--where-data`, `--select`) at runtime, allowing an outsider to inject free-text into the query construction workflow before any specific item selection.
- 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.