Security audit
Cn Text Statistics
Security checks across malware telemetry and agentic risk
Overview
The skill set is mostly coherent for ClawHub and Convex maintainer work, but it includes a review helper that defaults to running nested Codex with full filesystem access and approval bypass.
Install only if you trust the publisher and need ClawHub maintainer or Convex development workflows. Before using autoreview, consider disabling full-access mode with `--no-yolo` or `AUTOREVIEW_YOLO=0`, and review any moderation, GitHub publishing, migration, or auth setup command before allowing it to run.
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
65/65 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.