Skills
skills/magentosh/skills/llm-models/Socket

llm-models

Warn

Audited by Socket on Jul 23, 2026

1 alert found:

Security
SecurityMEDIUM
SKILL.md

SUSPICIOUS: the skill's purpose is coherent, but it relies on a broad-permission external CLI, mutable install references, and transitive skill installation. This looks more like a high-trust platform wrapper than a narrowly scoped skill; main risk is supply-chain and credential/data forwarding, not confirmed malware.

Confidence: 84%Severity: 72%
Audit Metadata
Analyzed At
Jul 23, 2026, 06:04 PM
Package URL
pkg:socket/skills-sh/magentosh%2Fskills%2Fllm-models%2F@200ee2022d23de99481d60e1b81f00dc2f5bf88205d681c9a3fd6fd07f9f61f6
Security Audit — socket — llm-models