execute

Warn

Audited by Snyk on Mar 1, 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 explicitly instructs launching WebSearch/WebFetch for "Web research" (Phase 4 Execution rules and the references/agent-selection.md decision flow), meaning it will fetch and interpret open/public web content that can influence task planning and tool actions, exposing the agent to untrusted third-party content.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 1, 2026, 01:36 AM