research

Warn

Audited by Snyk on Mar 10, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The skill's required Step 2 "Web Search Supplement" instructs launching a web-search-agent to fetch and incorporate external web sources (see the hard-constrained prompt template and "Sources
  • Source1"), meaning the agent will read and use untrusted public web content to supplement items and fields that materially influence subsequent research outputs.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 10, 2026, 07:06 PM