Agent Rating Protocol
Security checks across malware telemetry and agentic risk
Overview
This skill is a straightforward agent reputation helper, with the main caution that it asks users to install a third-party Python package and stores local rating records.
Install only if you are comfortable trusting the `agent-rating-protocol` Python package. Prefer a virtual environment, consider pinning a reviewed version, keep rating files in a known location, and avoid putting private transaction details into rating explanations or exported credentials.
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.