Ai Claims Assessment
Security checks across malware telemetry and agentic risk
Overview
The skill set is coherent and transparent, but it includes powerful repo, GitHub, Convex, and moderation workflows that should be run only with the intended credentials and targets.
Install only if you intend to use these ClawHub/Convex maintainer workflows. Before running moderation, migration, deploy, proof publishing, or autoreview helper commands, confirm the target, environment, and credentials are correct, and consider using the autoreview no-yolo option when full local access is unnecessary.
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.