connect

Warn

Audited by Socket on Aug 6, 2026

1 alert found:

Security
SecurityMEDIUM
SKILL.md

SUSPICIOUS: the skill is internally consistent with its stated purpose and uses official package sources, but it grants broad real-world action capability and routes credentials/actions through Composio-managed infrastructure. This is not confirmed malware, but it is a high-impact integration skill with meaningful credential-forwarding and autonomy risk.

Confidence: 90%Severity: 74%
Audit Metadata
Analyzed At
Aug 6, 2026, 04:56 PM
Package URL
pkg:socket/skills-sh/aiagentskills%2Fskills%2Fconnect%2F@376af7dbf1d269ad8aeecfb835c5f63551c6ac4b38d48ae1d71432482949cfff
Security Audit — socket — connect