Security audit
Snowflake
Security checks across malware telemetry and agentic risk
Overview
The available scanner telemetry is clean, and no workspace artifact evidence showed unsafe behavior, but the actual skill files were not present for full verification.
The telemetry is clean, but because the actual skill files were not available for this adjudication, review the published SKILL.md before installing, especially any commands, credential requests, network services, or account-changing actions it asks the agent to use.
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
63/63 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.