research-prospect

Warn

Audited by Snyk on Mar 7, 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 explicitly instructs the agent to navigate and read untrusted public third-party sources — the prospect's company website and the contact's LinkedIn profile (see "Research the Company" and "Research the Contact" and "Use browser tools for LinkedIn") — and to use that content to determine outreach hooks and next actions, which could allow indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 7, 2026, 01:34 PM