NYC

dependency-upgrade

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: 0.70). This skill explicitly fetches public third-party content (for example: curl https://raw.githubusercontent.com/facebook/react/main/CHANGELOG.md) which an agent following the workflow would read/interpret as part of upgrade analysis, exposing it to untrusted public content and potential indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 09:03 PM