tavily

Warn

Audited by Snyk on May 4, 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 instructs using Membrane to connect to Tavily — "Tavily is an AI-powered search engine ... find and synthesize information from the web" — and to run membrane action list/run to retrieve search/article results (returned in the action "output"), so the agent will ingest open web content from untrusted public sources that can influence subsequent actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 4, 2026, 11:41 AM
Issues
1