yandex-direct

Warn

Audited by Socket on Sep 11, 2026

1 alert found:

Security
SecurityMEDIUM
SKILL.md

SUSPICIOUS. The skill’s purpose and Yandex-specific credentials are coherent, and its documented data flows point to official Yandex OAuth/API endpoints. The main risk is install trust: it relies on an unverified npx package that receives a live OAuth token and can perform real advertising mutations, making the overall footprint high-risk despite otherwise plausible purpose alignment.

Confidence: 88%Severity: 78%
Audit Metadata
Analyzed At
Sep 11, 2026, 06:50 AM
Package URL
pkg:socket/skills-sh/artgas1%2Fyandex-direct-mcp%2Fyandex-direct%2F@dd9ccded2b3a53173b3e23b8cb7b45fd067a5fe58c75eb6684df0048e466fd73