websearch-quick

Warn

Audited by Snyk on Feb 15, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.70). This skill instructs the agent to run web searches and extract answers from open public sites via the WebSearch tool (e.g., GitHub releases, npm/PyPI, and community sources like Stack Overflow), and it will read and interpret those third‑party pages as part of its workflow, exposing it to untrusted/user-generated content and thus potential indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 10:40 PM