Security audit
turingnet-iran-connectivity-engineer
Security checks across malware telemetry and agentic risk
Overview
The skill is mostly safe troubleshooting guidance, but it makes unsupported claims about bundled safety scripts and includes an uninspected external self-heal shell integration.
Install only if you want the included privacy-preserving connectivity templates and guidance. Do not rely on the advertised redactor, triage, rate limiter, or report scripts unless they are separately provided and reviewed, and do not run the external sandbox-selfheal-guard command without inspecting that separate skill and understanding what it changes.
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
61/61 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.