Security audit
mbk
Security checks across malware telemetry and agentic risk
Overview
The skill artifacts are coherent with their stated workflow purposes, with sensitive API access disclosed and tied to user-directed operational tasks.
Install only if you expect the agent to help with ClawHub/OpenClaw, Convex, Axiom, Sentry, Slack, or release workflows. Configure API tokens with least privilege, review commands before destructive or public actions, and be aware that some helper scripts can read local credentials and write operational memory or remote service state when invoked.
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.