APort Agent Guardrail
Security checks across malware telemetry and agentic risk
Overview
This appears to be a legitimate guardrail skill, but it asks users to run an external installer that persistently changes how every OpenClaw tool call is handled.
Install only if you trust APort and want it to mediate every OpenClaw tool call. Prefer a test profile first, inspect or pin the npm package or GitHub revision, verify the current package name, decide local versus hosted logging deliberately, and confirm how to disable or remove the installed plugin before using it with sensitive accounts or data.
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
66/66 vendors flagged this skill as clean.