search

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 explicitly issues WebSearch queries and uses WebFetch(url=result.url, prompt="Extract key findings") to retrieve and read content from arbitrary public URLs (e.g., search results/initial_results), which can include untrusted or user-generated third-party sites and will be interpreted by the agent.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 12:21 AM