NYC

linux-apps

Warn

Audited by Snyk on Feb 16, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.80). The skill includes commands to open arbitrary URLs (e.g., "xdg-open https://example.com") and to screenshot browser windows (import/scrot targeting Firefox), so it can display and ingest untrusted public web content from arbitrary sites.

MEDIUM W013: Attempt to modify system services in skill instructions.

  • Attempt to modify system services in skill instructions detected (high risk: 0.70). The prompt explicitly includes a sudo apt-get install step (requesting elevated privileges) and contains commands that start/kill processes and modify the desktop/filesystem (screenshots), so it asks for privileged actions that can change the machine state.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 03:38 AM