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