Security audit
Ai Paper Cutting
Security checks across malware telemetry and agentic risk
Overview
The reviewed skill artifacts are coherent, disclosed, and purpose-aligned, with no artifact-backed evidence of malicious or hidden behavior.
Install only if you expect ClawHub/Convex workflow assistance and are comfortable with skills that can guide authenticated admin, migration, email, and external review-tool commands. Review commands before approval, especially production, destructive, transfer, ban, email-send, or migration apply steps.
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.