Security audit
Polsia Render Infrastructure
Security checks across malware telemetry and agentic risk
Overview
The reviewed skills are high-authority ClawHub maintenance and development helpers, but their sensitive actions are disclosed, purpose-aligned, and gated by user/admin controls.
Install only if you want repo-local ClawHub operator and development workflows. Several skills can guide production-impacting admin actions or send code review context to external model CLIs, so use them from the intended ClawHub repo with the normal auth controls and review dry-run/confirmation steps before writes or emails.
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
64/64 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.