Security audit
CollegeFootballData
Security checks across malware telemetry and agentic risk
Overview
The skill materials mostly fit legitimate ClawHub maintenance workflows, but one review helper defaults to launching nested Codex with full-access sandbox bypass, which deserves manual review before installation.
Install only if you trust the publisher and intend to use these ClawHub maintainer workflows. Treat moderation and proof-publishing commands as production-impacting, verify targets and reasons before writes, and consider disabling autoreview full-access mode with --no-yolo or AUTOREVIEW_YOLO=0 unless you explicitly want nested Codex to run with broad local authority.
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
VirusTotal findings are pending for this skill version.
Static analysis
No suspicious patterns detected.