session-debrief
Warn
Audited by Socket on Oct 8, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the skill's behavior broadly matches its stated purpose, but it processes sensitive local session transcripts and forwards them to a configurable third-party LLM endpoint using locally sourced credentials. The main concern is data-flow integrity and endpoint trust, not overt malware or command injection.
Confidence: 90%Severity: 76%
Audit Metadata