agenta

Warn

Audited by Socket on Mar 27, 2026

1 alert found:

Security
SecurityMEDIUM
SKILL.md

SUSPICIOUS: the skill’s crypto-payment purpose matches its capabilities, but it combines remote installer execution, third-party credential handling, custom-server routing, and autonomous financial actions. This is a coherent but high-risk wallet/payment skill rather than clearly malicious content.

Confidence: 85%Severity: 84%
Audit Metadata
Analyzed At
Mar 27, 2026, 05:01 PM
Package URL
pkg:socket/skills-sh/AgentaOS%2Fskills%2Fagenta%2F@ff24eb1e27952d6467a76a270b3560e3d54808a7