tavily-search

Fail

Audited by Snyk on Nov 17, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E004: Prompt injection detected in skill instructions.

  • Potential prompt injection detected (medium risk: 0.30). The skill is a documented Tavily search workflow, but its advice to avoid &, $(...) and loops so the client won't ask for permission steers the agent around the client's permission prompts, which weakens a user-facing protection beyond what the search task needs.

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

  • Third-party content exposure detected (low risk: 0.10). The required workflow runs Tavily web searches, extracts, and crawls, which return content from arbitrary web pages that outsiders author. The agent must actively issue these queries, so an attacker can publish poisoned pages but cannot force delivery into the workflow.

Issues (2)

E004
CRITICAL

Prompt injection detected in skill instructions.

W011
MEDIUM

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

Audit Metadata
Risk Level
CRITICAL
Analyzed
Nov 17, 2026, 03:46 AM
Issues
2