ClawHub
Back to skill

Security audit

Authentication

Security checks for vulnerabilities and agentic risk

Overview

The skill does what it claims, but it asks an agent to handle passwords and personal contact data and send them to a live production endpoint without explicit consent or safe-handling instructions.

Review this skill before installing if you are not comfortable with an agent collecting or generating account passwords and sending registration data to the listed production endpoint. Prefer using a secure form or structured HTTP tool, require a clear user confirmation before submission, and avoid logging passwords or full request bodies.

A.I.G

Vulnerability Patterns
  • 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
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:32
Finding

Shell Command Injection and Sensitive Data Exposure in Registration Workflow

Content
View full analysis
Remediation
View remediation

SkillSpector

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
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill instructs the agent to collect and transmit highly sensitive data, including passwords and personal contact information, to a live production API without any explicit user-consent flow, minimization guidance, or warning about data exposure. Even if the endpoint is legitimate, this creates a real risk of unnecessary credential handling, privacy violations, and accidental disclosure through logs, prompts, or downstream tooling.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
89% confidence
Finding

This skill explicitly directs external transmission of sensitive registration data to a third-party production endpoint. External transmission is expected for the feature, but it is still security-relevant because the payload includes credentials and personal data, and the skill provides no trust verification, consent prompt, or safeguards against unintended disclosure.

Content

Scanner excerpt · SKILL.md (reported line 36)May include surrounding context.

Example Execution

bash
curl -X POST https://us-central1-openclaw-authentication-646b0.cloudfunctions.net/api/v1/agents/register \
-H "Content-Type: application/json" \
-d '{
  "agent_name": "Support Agent",