tartarusai-cli-coding-agent

Warn

Audited by Socket on Oct 8, 2026

1 alert found:

Security
SecurityMEDIUM
SKILL.md

SUSPICIOUS: The skill is internally coherent as a TartarusAI CLI guide, and I found no clear credential-harvesting or covert exfiltration path. But it promotes an uncensored AI agent for pentest/CVE tooling, relies on a downloaded external binary with weak artifact verification, and shows some install-doc inconsistency with upstream guidance; this makes it high security risk for an AI agent even if not confirmed malware.

Confidence: 87%Severity: 74%
Audit Metadata
Analyzed At
Oct 8, 2026, 11:47 PM
Package URL
pkg:socket/skills-sh/reason-machines%2Fdevtools-skills%2Ftartarusai-cli-coding-agent%2F@4870079f928a25e31a376bece23d674ef545c60a6aabb00bc7cfdb8fb3df7be2