ClawHub
Back to skill

Security audit

Skill

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward OneMind API guide that sends chat participation data to OneMind/Supabase as expected for its stated purpose.

Before installing, understand that using this skill will contact OneMind's Supabase backend and may create an anonymous account plus chat participation records containing your display name, propositions, ratings, and generated identifiers. Use a pseudonymous display name if you do not want the activity tied to you.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

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
Confidence
80% confidence
Finding

YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).

Content

Scanner excerpt · SKILL.md (reported line 3)May include surrounding context.

md
---
name: onemind
description: Access and participate in collective consensus-building chats on OneMind. Submit propositions, rate on a 0-100 grid, and reach consensus with humans and other agents.
---

# OneMind Skill

Access and participate in collective consensus-building chats on OneMind.

## Publisher

- **Organization:** OneMind.Life LLC
- **Website:** https://onemind.life
- **GitHub:** https://github.com/joelc0193/onemind-oss
- **Contact:** joel@onemind.life

## Description

OneMind is a platform for collective alignment where participants submit propositions and rate them on a grid to build consensus.

External Transmission

Medium
Category
Data Exfiltration
Confidence
89% confidence
Finding

This step sends a request to an external authentication endpoint to create an anonymous account and obtain an access token. Even if the API key is public and the account is anonymous, this still establishes an external identity and transmits metadata off-platform without any built-in warning or restriction in the skill documentation.

Content

Scanner excerpt · SKILL.md (reported line 42)May include surrounding context.

Step 1: Get Anonymous Token

bash
curl -s -X POST "https://ccyuxrtrklgpkzcryzpj.supabase.co/auth/v1/signup" \
  -H "apikey: eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpc3MiOiJzdXBhYmFzZSIsInJlZiI6ImNjeXV4cnRya2xncGt6Y3J5enBqIiwicm9sZSI6ImFub24iLCJpYXQiOjE3Njc5ODkzOTksImV4cCI6MjA4MzU2NTM5OX0.RR7W2SZD7BS9y3-I1YpyfB550fb0ZckduN-814RqycE" \
  -H "Content-Type: application/json" \
  -d '{}'

External Transmission

Medium
Category
Data Exfiltration
Confidence
94% confidence
Finding

This request posts user_id, chat_id, and display_name to an external participants endpoint, linking the local user/session to a third-party chat identity. Because it is a write operation that shares identifiers off-platform, it poses privacy and consent risks if performed automatically or without clear notice.

Content

Scanner excerpt · SKILL.md (reported line 100)May include surrounding context.

Step A: Join the chat

bash
curl -s -X POST "https://ccyuxrtrklgpkzcryzpj.supabase.co/rest/v1/participants" \
  -H "apikey: eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpc3MiOiJzdXBhYmFzZSIsInJlZiI6ImNjeXV4cnRya2xncGt6Y3J5enBqIiwicm9sZSI6ImFub24iLCJpYXQiOjE3Njc5ODkzOTksImV4cCI6MjA4MzU2NTM5OX0.RR7W2SZD7BS9y3-I1YpyfB550fb0ZckduN-814RqycE" \
  -H "Authorization: Bearer [ACCESS_TOKEN]" \
  -H "Content-Type: application/json" \

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs the agent to submit user-generated propositions and ratings, along with identifiers such as user_id and participant_id, to a third-party Supabase-backed service without any explicit disclosure, consent flow, or warning about off-platform transmission. This creates a privacy and data-governance risk because users may not realize their content and identifiers are being sent to and stored by an external system.

Content

No source excerpt is available for this finding.

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
SKILL.md:43