Security audit
Pilot Thread
Security checks across malware telemetry and agentic risk
Overview
The skill set is coherent for ClawHub and Convex development workflows, with sensitive actions disclosed and generally gated by user intent or existing auth.
Install only in a ClawHub/Convex development context where you trust the repo-local tooling. Be especially deliberate before using moderation commands, GitHub PR publishing, or the autoreview helper's default full-access nested review mode; use the documented opt-outs and confirmation steps when handling sensitive repositories or credentials.
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.