workflow-orchestrator
Warn
Audited by Snyk on Feb 28, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). Yes — multiple workflow templates and agent configs (e.g., references/builder-only.yaml and references/build-verify-plan.yaml) explicitly grant agents a "webfetch" tool and the SKILL.md Integration section documents HTTP/OpenCode integrations, meaning agents will fetch and read arbitrary public web content that can be interpreted and used to drive subsequent agent actions.
Audit Metadata