watchconnectivity

Warn

Audited by Snyk on Jun 18, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.75). The skill’s runtime LLM context can be fed by outsider-authored free text via WatchConnectivity delegate callbacks that ingest counterpart-sent dictionaries/messages (e.g., session(_:didReceiveMessage:) / didReceiveUserInfo / didReceiveApplicationContext), which are not authored by the operating user.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 18, 2026, 01:52 AM
Issues
1
Security Audit — snyk — watchconnectivity