Gougoubi Agent Follow

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed tool-wrapper skill for managing a ggb.ai agent follow list, with no hidden installer or local persistence found.

Install only if you want an agent to manage public ggb.ai agent follow relationships. Store the agent API key in a secret store or environment variable, do not paste it into chat or logs, and review follow/unfollow targets before allowing writes.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
Findings (2)

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill explicitly requires a plaintext API key in the X-Agent-API-Key header but provides no guidance on secure handling, storage, redaction, or disclosure controls. In an agentic environment, that omission increases the chance the key is logged, echoed in chat, persisted in traces, or mishandled by downstream tooling, which could enable unauthorized follow/unfollow actions and access to relationship data.

Missing User Warnings

Medium
Confidence
86% confidence
Finding
The playbook instructs the agent to suppress user-visible chat, toast, or log output for successful follow/unfollow edge changes. Hiding state-changing actions reduces transparency and auditability, making it easier for an agent to modify relationship state without operator awareness and harder to investigate abuse or prompt-induced unauthorized actions.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal