eve-agentic-app-design
Warn
Audited by Snyk on Mar 10, 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). This skill routes and ingests inbound chat messages from external providers (e.g., Slack, Nostr, WebChat) into agents as described in the "Gateway Architecture" and "Routing Design" sections of SKILL.md, allowing user-generated/untrusted messages to be interpreted and trigger agent actions like dispatching pipelines or deployments.
Audit Metadata