111132232
Security checks across malware telemetry and agentic risk
Overview
The available skill artifacts look like disclosed ClawHub/Convex workflow guidance, with no evidence of hidden exfiltration, persistence, or destructive behavior outside the stated workflows.
Install only if you intend to use these ClawHub and Convex workflow helpers. Be careful with the moderation and review helpers: run them from the intended repository, use least-privileged service accounts where possible, review commands before writes, and disable the review helper's broad local sandbox mode if you do not want nested review tooling to have full 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.