Hermes Agent Health Check
Security checks across malware telemetry and agentic risk
Overview
This is a coherent Hermes Agent audit skill; its main risk is the normal caution of installing and running a third-party Python scanner on local source code.
Install only if you are comfortable running the `hermescheck` Python package on the repository being audited. Use a virtual environment or container, consider pinning or inspecting the package first, and review generated JSON, Markdown, or SARIF reports before sharing them because they may contain local paths or secret-detection evidence.
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
65/65 vendors flagged this skill as clean.