agent-platform-troubleshooting
Warn
Audited by Snyk on Jul 29, 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). In
SKILL.mdthe required runtime diagnostic flow gathers evidence by querying Google Cloud logs (Agent/Gateway/IAP) viamcp__gcloud-observability__list_log_entries/gcloud logging read, which ingests outsider-authored free text coming from users/request bodies and thus can be subject to indirect prompt injection.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata