operate

Warn

Audited by Snyk on Jun 15, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 0.80). The skill's Research step explicitly requires using WebSearch/WebFetch to retrieve external articles (arbitrary web article URLs discovered at runtime via WebFetch) and then inject and process that fetched content to create insights, so runtime external URLs would directly control the agent's prompts/outputs.

Issues (1)

W012
MEDIUM

Unverifiable external dependency detected (runtime URL that controls agent).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 15, 2026, 09:45 AM
Issues
1
Security Audit — snyk — operate