Security audit
Talent Profile Generator
Security checks across malware telemetry and agentic risk
Overview
The skill set is coherent ClawHub maintainer automation, but one review helper defaults to launching a nested reviewer with full sandbox bypass permissions.
Review the autoreview workflow before installing or invoking it. Use the safer --no-yolo option unless you intentionally want a nested reviewer to run with full local access, and avoid running the helper on repositories or untracked files containing secrets. Staff moderation and PR-publishing skills should be used only with the intended ClawHub accounts and explicit targets.
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
61/61 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.