gke-workload-identity
Warn
Audited by Snyk on Oct 20, 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 instructs the agent to read Kubernetes workload and system logs (via
kubectl logsand Cloud Logging), which contain application-level output and error messages potentially influenced by external callers or user input.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata