Security audit
AgentSafe Scan
Security checks across malware telemetry and agentic risk
Overview
This skill is a disclosed external static-scan helper for remote skill installs, with no hidden execution or local persistence found.
Install only if you are comfortable sending skill URLs or pasted skill content to the AgentSafe hosted API. Do not include secrets, credentials, private files, or personal data in scan payloads, and treat scanner results as advisory rather than proof that a skill is safe.
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
64/64 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.