Caveat verdict
swift-mlx-lm
mlx-swift-lm
Receives external input AND uses eval
Reference documentation for the MLX Swift LM library covering local inference, LoRA fine-tuning, and embeddings on Apple Silicon; no network calls or exfiltration patterns present.
Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
What it does
These are capability combinations: each listed behavior occurs in the skill, but Caveat detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.
Receives external input AND uses eval — the remote code-injection pattern (data-flow not verified)
LLM01 · LLM05 · ASI01 · ASI05
Encodes data AND uses eval — the obfuscated-execution pattern (atob + eval; data-flow not verified)
LLM05 · ASI05 · ASI10
Findings (3)
Uses eval() — can execute arbitrary code
SKILL.md · code · eval(
Possible hardcoded credential
references/model-container.md · code · Token: "your_token
Popular HTTP library — network access
references/tool-calling.md · code · got
Permissions & capabilities
No declared permissions — minimal attack surface.
dynamic_evaldata_encodingnetwork_in Thanks — recorded.