ClawHub
Back to skill

Security audit

Ouroboros

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent relay to an external Ouroboros MCP workflow, but it delegates repository and execution-related work to an unpinned external package with limited scoping or disclosure.

Install only if you trust the external Ouroboros MCP server and the `ouroboros-ai` package. Before using it in private channels or important repositories, review or pin the MCP package version and confirm what `repo`, `run`, and stored message identifiers allow the service to access or retain.

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 (1)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill explicitly instructs the agent to always forward `channel_id`, `guild_id`, `user_id`, and optionally `message_id` to the external MCP tool, but provides no user-facing notice, consent flow, or minimization guidance. This creates a privacy and data-governance risk because identifiable metadata is transmitted to another service whenever the `ooo` prefix is used, and the relay-only design reduces opportunities for the agent to warn the user or redact unnecessary fields.

VirusTotal

58/58 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.