Caveat verdict
mlx-local-inference
Accesses credentials AND makes external network calls
Local MLX inference stack for Apple Silicon; all calls go to localhost:8000/v1 via oMLX or local Python libraries — entirely offline, purpose-appropriate, no external exfiltration.
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.
Accesses credentials AND makes external network calls — potential credential theft
LLM02 · ASI03
Permission integrity
network_out
credential_access
Findings (2)
Pipe-to-shell pattern (curl | sh) — supply chain attack vector
SKILL.md · prose · downgraded · curl -LsSf https://astral.sh/uv/install.sh | sh
Pipe to sh — executes piped content as shell commands
SKILL.md · prose · downgraded · | sh
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
No declared permissions — minimal attack surface.
credential_accessnetwork_outnetwork_in Thanks — recorded.