helm
Warn
Audited by Snyk on Nov 21, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The skill's only outsider-influenced text path is
helm search hub, which the agent must actively run to query Artifact Hub's community chart descriptions, so exposure requires the agent to fetch it (low), not a monitored inbox or feed (medium).
MEDIUM W013: Attempt to modify system services in skill instructions.
- Attempt to modify system services in skill instructions detected (low risk: 0.10). Helm install, upgrade, rollback, and uninstall commands change live Kubernetes releases, but the skill gives no explicit text establishing unrecoverable operational loss, so gate 2 fails and the tier is low.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W013
MEDIUMAttempt to modify system services in skill instructions.
Audit Metadata