Effect AI
Warn
Audited by Snyk on Feb 16, 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). The skill defines a searchTool described as "Search the web" and an AiPlan that feeds those search results (context.previousResults) into subsequent analysis steps, meaning the agent is intended to fetch and read untrusted/open-web content (third-party search results) as part of its workflow.
Audit Metadata