service-ingress

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 (medium risk: 0.30). The skill is static Kubernetes reference material, but its troubleshooting steps have the agent read Ingress-NGINX controller logs (lines 296-297, 376), which record attacker-controllable request paths and headers from internet traffic.

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 documents kubectl operations that change the cluster (expose, delete svc, create TLS and basic-auth secrets), but the file gives no explicit evidence of unrecoverable operational loss, so it fails the irreversibility gate and stays at low.

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 21, 2026, 11:43 AM
Issues
2