ClawHub
Back to skill

Security audit

Ai Code Generator

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward code-generation skill that discloses project file generation and does not show credential theft, persistence, or hidden execution behavior.

Before installing, treat generated code as untrusted until reviewed. Run it in a normal project workspace, choose where files are written, check for overwrites, and do not include secrets in prompts or generated .env files.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · index.js (reported line 251)May include surrounding context.

js
\`\`\`

3. **Configure Environment**
   - Copy .env.example to .env
   - Update environment variables

4. **Run Tests**

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill explicitly advertises file generation and a workflow step to 'Write to file', but it does not clearly disclose that it will modify the local filesystem or describe boundaries for where files may be written. In an agent ecosystem, this can lead users to authorize a skill without understanding it may create or overwrite multiple files, increasing the risk of unintended filesystem changes.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.