gcloud
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 is a gcloud CLI command reference, but the optional
gcloud logging readandgcloud functions logs readexamples can return log entries that contain request-derived text from publicly reachable--allow-unauthenticatedendpoints, which an outsider can influence, though the agent must run these commands itself.
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 state-changing GCP operations (creating, stopping, deleting, and resizing instances, firewall and IAM changes, cluster upgrades, and public ACL grants), but no supplied text establishes explicit irreversible 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