NYC

langchain

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's "Multi-Tool Research Agent" explicitly instantiates DuckDuckGoSearchRun and WikipediaQueryRun (with WikipediaAPIWrapper) to fetch and ingest open-web and Wikipedia content that the agent reads and uses in its workflow, exposing it to untrusted/user-generated third-party data.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 11:06 AM