Security audit
"Dictionary"
Security checks across malware telemetry and agentic risk
Overview
The skill appears to be a disclosed set of ClawHub and Convex workflow helpers with no evidence of hidden execution or malicious behavior.
Install only if you intend to use it for ClawHub or Convex maintenance workflows. Review the moderation and autoreview helpers before use, especially commands that can change public state, use account credentials, or run nested review with broad local access.
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
65/65 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.