deep-searcher-guide

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). The SKILL.md explicitly shows ingesting public web content (HTML support) and adding a WebSearchSource (Integration with Research Tools section) so the agent fetches and reads untrusted public web pages as part of the iterative RAG workflow, which can materially influence its queries and actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 10, 2026, 07:33 AM