autoskill
Warn
Audited by Snyk on Oct 2, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The workflow queries a local screenpipe daemon API (via fetch_window.py) which returns historical screen capture data, including window titles and OCR text from any applications and web pages the user viewed, exposing the agent to untrusted external content.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata