Security audit
Ai Pedology
Security checks across malware telemetry and agentic risk
Overview
The skill artifacts are purpose-aligned operational guidance with disclosed high-impact admin and review workflows, but no hidden install hooks, exfiltration, or automatic destructive behavior were found.
Install only in a ClawHub/Convex staff or development environment where you are comfortable with repo-local admin commands and external code-review engines. For staff actions, verify the target account, deployment, recipient, and command before approving writes or sends.
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.