Security audit
linkedin-posts
Security checks across malware telemetry and agentic risk
Overview
The visible skill artifacts are coherent ClawHub and Convex maintainer aids, with powerful but disclosed commands that require careful use.
Install only if you are doing ClawHub or Convex maintainer work and are comfortable with local CLI execution and authenticated GitHub/Convex operations. Use moderation and publishing commands only with explicit targets and reasons, and consider running autoreview with its safer no-yolo option when sandbox bypass is not needed.
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.