Security audit
Deepscan Monitor
Security checks across malware telemetry and agentic risk
Overview
This is an instruction-only skill for starting and monitoring PapersFlow DeepScan research jobs, with no hidden code or local system access found.
Safe to install for DeepScan workflows. Be aware that DeepScan jobs and stored reports may involve sending research prompts or report data to the configured PapersFlow service, so avoid using sensitive material unless that sharing is intended.
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.
Static analysis
No suspicious patterns detected.