Claude Skills Agent Protocol
Security checks across malware telemetry and agentic risk
Overview
This is a markdown-only coordination guide for business-role agents, with no evidence of hidden execution, credential access, exfiltration, or destructive behavior.
This skill appears safe to install as a coordination and formatting guide. Users should understand that it may influence how agents structure business recommendations and may prompt decision logging or context updates if the surrounding agent system supports those actions, so those workflows should remain user-directed.
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.