Security audit
Water Park Guide
Security checks across malware telemetry and agentic risk
Overview
The skill is a coherent water-park search helper, but it tells the agent to automatically install an unpinned global travel CLI before answering.
Install only if you are comfortable with a third-party FlyAI/Fliggy CLI being installed globally and used for your travel searches. Ask the agent to request confirmation before running `npm i -g @fly-ai/flyai-cli`, verify the package source/version yourself, and treat returned booking links as provider-backed results rather than an independent survey of all options.
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
60/60 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.