Security audit
taskflow
Security checks across malware telemetry and agentic risk
Overview
The reviewed artifacts look like disclosed ClawHub maintainer/developer guidance, with powerful actions described but not hidden or automatic.
Install only if you are working on ClawHub or intentionally want repo-local maintainer workflows. Be especially careful with moderation commands, GitHub/Convex credentials, and the autoreview helper's full-access review mode; run those only when you understand the target and expected side effects.
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.
