mnemos
Warn
Audited by Socket on Jul 14, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the skill’s purpose mostly matches its local checkpointing and transcript-ingestion behavior, and there is no clear network exfiltration. The main issue is install/execution trust: it relies on an undocumented mnemos CLI/binary with unverifiable provenance, while also processing sensitive local transcript data and injecting restored context automatically.
Confidence: 82%Severity: 72%
Audit Metadata