demo-prep

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 requires researching the prospect by visiting the company's website and looking up the contact on LinkedIn (Process step 2 and Instructions 1), meaning the agent ingests untrusted public web/social content that directly influences its outputs and subsequent actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 7, 2026, 01:34 PM