ClawHub
Back to skill

Security audit

Emulo

Security checks across malware telemetry and agentic risk

Overview

The skill is purpose-aligned but asks agents to automatically load a locally mined profile from prior AI session logs before work, which deserves user review.

Review the generated profile before allowing agents to use it broadly. Install only if you are comfortable with local AI session logs being mined into persistent agent guidance, and prefer using it only for tasks where that personalization is clearly wanted.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The skill explicitly instructs the agent to run a local profile loader before working on any task, which is overly broad and can trigger access to locally mined session data without clear user intent for each task. Because the profile is derived from prior AI session logs and is meant to influence future behavior, automatic invocation expands the trust boundary and can cause unnecessary exposure of sensitive preferences, history, or instructions.

YARA rule 'agent_skill_mcp_tool_poisoning_metadata': MCP/tool metadata poisoning indicators in tool schemas or skill manifests [agent_skills]

High
Category
YARA Match
Content
---
name: emulo
description: Load the user's Emulo profile, mined from their local Claude Code, Codex, and OpenCode session logs, so you work like them instead of a cold start. Use before working on their task.
emoji: 🐦‍⬛
homepage: https://github.com/ohad6k/emulo
metadata:
Confidence
81% confidence
Finding
The manifest description itself contains behavioral steering: it tells the agent to 'work like' the user and 'use before working on their task.' In a skill manifest, that kind of metadata can act as prompt-like control data that biases agent behavior and encourages pre-task execution of a local data-mining tool, which is a form of metadata/tool poisoning even if not overtly malicious.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.