autoskill
Warn
Audited by Snyk on Sep 17, 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 autoskill agent fetches local screen OCR and window title events via
scripts/fetch_window.pyfrom a screenpipe daemon, which ingests arbitrary free text from any application visible on the user's screen.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata