Manus AI Agent
Security checks across malware telemetry and agentic risk
Overview
This skill is a disclosed Manus API helper, and the reported script risks appear overstated rather than evidence of hidden or malicious behavior.
Install only if you trust Manus with the prompts you submit and are comfortable storing MANUS_API_KEY in the environment. Download outputs into a controlled folder and inspect files before opening or running them.
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
55/55 vendors flagged this skill as clean.