Security audit
Ai Anthropology
Security checks across malware telemetry and agentic risk
Overview
The available ClawHub skill artifacts describe high-impact maintainer workflows, but their authority is disclosed, scoped to operator tasks, and guarded by confirmation steps.
Install only in a trusted ClawHub maintainer environment. Several workflows can send email, alter moderation state, change ownership, or run production migrations, so use them with the documented dry-run and explicit signoff gates.
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
63/63 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.