ai-brain
Warn
Audited by Socket on Mar 14, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS: the stated purpose matches a memory skill, and no explicit exfiltration or third-party routing is shown, but the skill is designed for always-on autonomous profiling and depends on unseen local shell scripts. Main risks are privacy persistence, silent accumulation of user data, and unverifiable script behavior rather than confirmed malware.
Confidence: 80%Severity: 52%
Audit Metadata