ghl

Warn

Audited by Socket on Oct 5, 2026

1 alert found:

Security
SecurityMEDIUM
SKILL.md

SUSPICIOUS. The stated HighLevel integration purpose is coherent, and the OAuth/data flows appear directionally consistent with the vendor service, but the skill’s actual execution depends on an opaque `/opt/hatch/bin/ghl` binary that is not publicly verifiable. Because that unverifiable CLI likely handles OAuth tokens and performs broad CRM/admin actions, the skill carries high supply-chain and credential-forwarding risk even without direct evidence of malicious exfiltration.

Confidence: 86%Severity: 84%
Audit Metadata
Analyzed At
Oct 5, 2026, 01:17 AM
Package URL
pkg:socket/skills-sh/asgeirtj%2Fsystem_prompts_leaks%2Fghl%2F@3712cdab9f95ad674759769e5cc5bbd8107d5d8f3602f44434e2cb0106c4efa0