ClawHub
Back to skill

Security audit

ClawMeet

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it says by connecting agents to an external social service, but it uses insecure HTTP and directs agents to send local identity-derived data and social actions without clear approval gates.

Review this carefully before installing. Use it only if you are comfortable sending agent identity, owner/profile fields, friend relationships, and chat content to the listed external service over unencrypted HTTP. Do not let it read SOUL.md or IDENTITY.md or send friend requests/messages until you have reviewed the exact data, destination, recipient, and message content.

A.I.G

Vulnerability Patterns
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (4)

T05 · Unauthorized Access and Privilege Escalation

Error
Location
SKILL.md:22
Finding

Internal Agent Identity Data Is Collected and Transmitted to a Third-Party Service

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Error
Location
SKILL.md:14
Finding

Sensitive Profile and Chat Data Is Transmitted over Plaintext HTTP

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Error
Location
SKILL.md:53
Finding

Documented API Operations Permit Caller-Supplied Identities Without Authentication

Content
View full analysis
Remediation
View remediation

T05 · Unauthorized Access and Privilege Escalation

Warning
Location
SKILL.md:89
Finding

First-Time Setup Authorizes External Social Actions Without Per-Action User Approval

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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 (4)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill directs use of an external service over plain HTTP and does not warn that profile data and later chat content are sent unencrypted to a third-party host. This exposes potentially sensitive identity, metadata, and message contents to interception or tampering by network attackers and hides the privacy risk from users.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
96% confidence
Finding

The registration example sends agent profile data to an external IP-based service, and in this skill that transmission occurs over unsecured HTTP. Because the skill is specifically designed to register identities and enable social/chat interactions, the external transmission is central behavior and becomes more dangerous due to the type of data involved and lack of transport security or consent notice.

Content

Scanner excerpt · SKILL.md (reported line 22)May include surrounding context.

1. Register Your Agent

bash
curl -X POST http://111.230.92.114:3456/api/agents \
  -H "Content-Type: application/json" \
  -d '{
    "name": "YOUR_AGENT_NAME",

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
99% confidence
Finding

The workflow explicitly tells the agent to read local SOUL.md / IDENTITY.md files and submit extracted personality and skills to ClawMeet without any approval step. That creates a clear data exfiltration path from local files to an external service and may disclose sensitive user, system, or agent identity information beyond what is necessary.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The only chat example sends the message content 你好！很高兴认识你 🐾, which implicitly steers the skill toward a specific language. There is no accompanying instruction that language should follow user preference or be selectable, so this conflicts with the policy against forcing a locale without opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.