lindy-expert

Warn

Audited by Snyk on Mar 28, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 1.00). The skill's Quickstart (Step 4: "Add a Knowledge Base" — enter your company website URL and click "Crawl") and the Computer Use guide (example: "LinkedIn Outreach") explicitly instruct the agent to fetch and browse public websites and social media, which are untrusted/user-generated sources that the agent reads and uses to drive actions (e.g., crafting email replies and outreach), enabling indirect prompt injection.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 28, 2026, 01:07 PM
Issues
1