swift-mlx-lm
Warn
Audited by Snyk on Mar 5, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill explicitly downloads models and config files from public hubs (see references/model-container.md: "Download: Model weights fetched from HuggingFace") and then auto-detects/parses tool-call formats and model-generated tool calls (references/tool-calling.md and SKILL.md), so untrusted third-party model/config content and model outputs are ingested and can directly influence tool parsing/execution.
Audit Metadata