agent-tools

Warn

Audited by Socket on Apr 14, 2026

1 alert found:

Security
SecurityMEDIUM
SKILL.md

SUSPICIOUS: the core inference.sh CLI usage appears aligned with the stated platform and uses same-org infrastructure, so this is not confirmed malware. However, the skill has medium-high security risk because it relies on an unpinned remote installer, uploads local files to cloud services, enables autonomous public/social actions, and instructs transitive installation of additional third-party-managed skills.

Confidence: 87%Severity: 76%
Audit Metadata
Analyzed At
Apr 14, 2026, 11:27 PM
Package URL
pkg:socket/skills-sh/rafaelgrasa%2Fskills%2Fagent-tools%2F@2071a97c627653e044d6ffd8887c5365d08fd41f