Message
Security checks across malware telemetry and agentic risk
Overview
This is a documentation-only messaging guidance skill that helps draft safer messages and does not include code, persistence, or external access.
Safe to install as an instruction-only skill. When using it with real messaging tools, keep approval required for high-stakes or public messages, verify recipient and channel before sending, limit message-history context to what is needed, and avoid using tone matching to mislead recipients where disclosure is expected.
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
66/66 vendors flagged this skill as clean.