Security audit
个人健康教练
Security checks across malware telemetry and agentic risk
Overview
The skills are mostly coherent ClawHub/Convex workflow helpers, but one review helper defaults to running nested Codex review with full sandbox bypass, which is broader authority than a code-review skill needs by default.
Install only if you trust these repo-maintenance workflows. Pay particular attention to the autoreview helper: use `--no-yolo` or avoid that helper when you do not want a nested reviewer to receive broad local filesystem and command authority. For moderation or PR publishing workflows, confirm exact targets and commands before allowing writes.
SkillSpector
By NVIDIA
Vulnerability Patterns
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
VirusTotal
57/57 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.