Caveat verdict

mlx-local-inference

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

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.

5
security
40
transparency
70
maintenance

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.

Capability combination high

Accesses credentials AND makes external network calls — potential credential theft

LLM02 · ASI03

Permission integrity

Makes network requests but does not declare curl/wget in required binaries

network_out

Code accesses API keys/tokens but declares no environment variables

credential_access

Findings (2)

Pattern match high

Pipe-to-shell pattern (curl | sh) — supply chain attack vector

SKILL.md · prose · downgraded · curl -LsSf https://astral.sh/uv/install.sh | sh

Pattern match high

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
Check another skill Browse the registry Auditing your own skills or configs? Use the API