data-researcher

Warn

Audited by Snyk on Feb 27, 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.md workflow explicitly includes fetching and ingesting public third-party content—e.g., "Data discovery" and "Data collection" sections list "Web scraping" and "Public datasets"—so the agent is expected to read untrusted web content that can materially influence its analyses and actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 27, 2026, 09:37 AM