Security audit
Pexels
Security checks across malware telemetry and agentic risk
Overview
The available artifacts look like repo-local helper skills for ClawHub and Convex workflows, with powerful maintainer commands disclosed and gated by user direction.
Install only if you trust the publisher with ClawHub maintainer or Convex development workflows. These skills can guide an agent to run powerful authenticated commands, so review requested commands before approval and use accounts/tokens with the least privileges 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
58/58 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.