Security audit
xnyjobsearch
Security checks across malware telemetry and agentic risk
Overview
The reviewed skills are repo-focused workflow helpers with powerful but disclosed ClawHub, GitHub, and Convex actions guarded by user direction and verification steps.
Install only if you are comfortable with repo-local maintainer automation that can use your existing ClawHub, GitHub, Convex, and model CLI credentials when you invoke those workflows. Review commands before approving moderation writes, role changes, proof publishing, or fallback model review, especially on private code.
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.