x-deep-research

Warn

Audited by Snyk on Feb 21, 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). This skill explicitly performs citation-backed research that requires finding and ingesting public web sources (e.g., SKILL.md "use when ... requiring web-sourced citations" and prompts/product.md "Find YouTube videos ... provide URL") so the agent will fetch and interpret untrusted third-party content (news, YouTube, public websites) as part of its workflow.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 21, 2026, 04:13 AM