Security audit
Lazaretto
Security checks across malware telemetry and agentic risk
Overview
This skill appears to be a straightforward pre-install checker that hashes user-selected files and calls the Lazaretto API, with no evidence of hidden execution, persistence, or credential theft.
Install only if you are comfortable with a third-party Lazaretto service receiving scan targets or inline file contents you explicitly choose to submit. Use the default API or a trusted --api endpoint, keep LAZARETTO_KEY scoped to this service, and avoid scanning private secrets as inline files unless you intend to send them for analysis.
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.