deep-research

Warn

Audited by Snyk on Feb 16, 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 Researcher agents explicitly use WebSearch and WebFetch to retrieve and save content from public websites (saved into research_notes/), which the Report-Writer then reads and synthesizes—so the agent ingests untrusted third-party web content as part of its workflow.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 01:01 AM