NYC

autonomous-cloud-orchestration

Warn

Audited by Snyk on Feb 15, 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). This skill's Browser service (services/browser/README.md) explicitly lets agents navigate to arbitrary URLs and extract web page content (see "Navigation" actions like {"action":"navigate","url":"..." } and "Content Extraction" examples), meaning the agent will fetch and interpret untrusted public web content which could be a vector for indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 09:15 PM