Hermes Feishu Guide

Security checks across malware telemetry and agentic risk

Overview

The skill appears related to its stated integration purpose, but its setup uses a risky remote shell installer and under-documented local credential storage.

Review the installer before running it, prefer pinned releases or checksums over curl-to-bash, and store API keys only in a private, git-ignored file or secret manager. Do not paste live credentials into chat or logs.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The guide tells users to place live API credentials in a local .env file but does not mention file permissions, exclusion from version control, or other safeguards. This can lead to accidental disclosure through permissive filesystem access, backups, shell history, screenshots, or committing the file to a repository.

Missing User Warnings

Medium
Confidence
98% confidence
Finding
Piping a remotely fetched script directly into bash executes network-supplied code without giving the user a chance to inspect it or verify its integrity. If the upstream repository, transport path, or referenced branch is compromised, users can suffer arbitrary code execution on their local machine.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal