autoskill
Warn
Audited by Snyk on Oct 1, 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 skill queries screenpipe's local
/searchendpoint to ingest window titles and OCR text, which can capture outsider-authored free text from web pages, documents, and messages viewed by the user.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata