kubectl

Warn

Audited by Snyk on Nov 22, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (medium risk: 0.30). The required workflow reads pod logs, describe output, and cluster-wide events from the user's own cluster via kubectl, and an outsider can influence that text by sending input to a public-facing workload whose application logs echo it, so the cluster-wide events and log reads in the helper scripts could surface attacker-influenced text without the agent selecting a specific outsider item.

MEDIUM W013: Attempt to modify system services in skill instructions.

  • Attempt to modify system services in skill instructions detected (low risk: 0.10). The skill exposes operations that change live clusters (apply, set image, scale, drain, delete, taint, and kubeconfig edits), but the supplied text never explicitly establishes unrecoverable loss of operational state, so the tier is low rather than medium or high.

Issues (2)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

W013
MEDIUM

Attempt to modify system services in skill instructions.

Audit Metadata
Risk Level
MEDIUM
Analyzed
Nov 22, 2026, 01:13 AM
Issues
2