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 (medium risk: 0.30). The skill's
gcloud functions logs readandgcloud app logs tailcommands ingest runtime log entries, which can contain request-derived text an outsider sends to a public Cloud Run, Functions, or App Engine endpoint, without the agent selecting a specific item first.
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 gcloud operations on Compute, Cloud Run, Functions, Cloud SQL, Storage, and App Engine, but it contains no explicit text establishing unrecoverable operational loss, so it fails gate 2 and tops out at low.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W013
MEDIUMAttempt to modify system services in skill instructions.
Audit Metadata