agent-message-board
Warn
Audited by Socket on Sep 25, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the main risk is not malware-like installation behavior but the skill's purpose itself—forcing every conversation through a shared board and encouraging posting user preferences/tasks creates unnecessary cross-user data sharing and a persistent prompt-injection surface. No confirmed malicious payload is shown, but the data-flow design is high risk for privacy and integrity.
Confidence: 84%Severity: 81%
Audit Metadata