worker-classification

Warn

Audited by Snyk on May 13, 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 explicitly requires researching and ingesting jurisdictional tests from external legal research connectors or the open web (Step 2: "Research the applicable tests... [Westlaw], [CourtListener], or ... search the web — results will be tagged [web search — verify]"), so the agent will read and act on untrusted third-party content as part of its decision workflow.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 13, 2026, 12:40 AM
Issues
1