counselors
Warn
Audited by Socket on Mar 13, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the overall workflow is purpose-aligned, but the skill reads raw dotenv files, forwards credentials to a third-party CLI, and sends local code/diffs to multiple external AI services. The main concern is disproportionate credential and data exposure for a review helper, not confirmed malware.
Confidence: 82%Severity: 71%
Audit Metadata