ke
Warn
Audited by Socket on Sep 20, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the skill’s stated purpose is coherent with local memory and research, and the flagged `rm -rf` is likely benign documentation. However, the main risk is install/execution trust: the core `ke` binary is an unverified local executable with web-fetch capability and background-hook integration, so the skill’s footprint cannot be fully assessed or trusted from the provided evidence.
Confidence: 87%Severity: 74%
Audit Metadata