injective-trading-autosign

Warn

Audited by Socket on Oct 9, 2026

1 alert found:

Security
SecurityMEDIUM
SKILL.md

SUSPICIOUS. The skill is internally coherent for Injective auto-trading, and I found no clear credential exfiltration or fake infrastructure. However, it enables autonomous financial transactions, reduces user approval friction by delegating trading authority to a session key, accepts a wallet password in the workflow, and expands trust by installing another skill. High security risk comes mainly from real-world trading autonomy and delegated signing authority, not from confirmed malware.

Confidence: 90%Severity: 79%
Audit Metadata
Analyzed At
Oct 9, 2026, 02:39 PM
Package URL
pkg:socket/skills-sh/injectivelabs%2Fagent-skills%2Finjective-trading-autosign%2F@2b33f5bd5adcbefcabec3f46eb46075af160a7aa9cdf8785d2521897768744e9