configure-container
Warn
Audited by Snyk on Apr 21, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill's Execution Step 2 explicitly instructs the agent to use WebSearch/WebFetch to check public third‑party sources (e.g., Docker Hub, GitHub release pages, aquasecurity/trivy-action) and to interpret those results before reporting or applying fixes, which exposes it to untrusted web content that can influence actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata