claude-code-operator
Warn
Audited by Socket on Oct 9, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS: the core Claude Code install path is legitimate and aligned with the skill's purpose, but the skill expands into third-party routing of prompts/content through BigModel and especially an external EdgeOne MCP endpoint. This is not confirmed malware, but data flows and off-platform integrations create medium risk and should be treated cautiously.
Confidence: 85%Severity: 56%
Audit Metadata