Copilot Research

Warn

Audited by Snyk on Mar 3, 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 Data Gathering and Error Handling sections explicitly require performing web searches and using public sources (company news, funding, leadership changes) as inputs for the brief, so untrusted third-party content from the open web is ingested and used to drive talking points, risks, and next actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 3, 2026, 11:37 AM