深度写作
Security checks across malware telemetry and agentic risk
Overview
The supplied scanner evidence does not show unsafe behavior, but the local workspace did not contain the specific skill artifact needed for a full artifact-backed review.
This looks safe based on the supplied scan context, but because the target skill artifacts were not available for full local inspection, review the actual SKILL.md and any install steps before installing, especially for commands that install software, request credentials, or run external tools.
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.