core-ml
Warn
Audited by Snyk on Apr 30, 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 explicitly downloads and loads models from arbitrary remote URLs (see "Remote Model Download and Update" in references/patterns.md — ModelUpdater.downloadModel(from: remoteURL: URL) and MLModelManager.compileAndCache(modelAt:sourceURL:) / model(at: URL) in templates.md), which ingests untrusted third‑party content that the agent will load and execute and thus can materially influence behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata