Security audit
double6-deep-research
Security checks across malware telemetry and agentic risk
Overview
This skill is a disclosed deep-research workflow with a local validator, and its file, web, and write behaviors are scoped to the user-authorized research task.
Before installing, be clear about which local materials and output directory the agent may use. The validator is a local Python checker for report structure and hashes, not an external fact verifier, so sensitive or high-stakes research still needs careful human review.
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.
Static analysis
No suspicious patterns detected.