ClawHub
Back to skill

Security audit

Automatic Test Generator

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only skill for generating unit tests, with one misleading example but no hidden execution, persistence, or data-handling behavior.

Safe to install from a security standpoint, but review generated tests carefully before relying on them. In particular, watch for tests that invent behavior the implementation does not actually provide, such as resilience or fallback semantics.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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
Findings (1)

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The documentation presents a test claiming the function should gracefully fall back to the database when cache access fails, but the shown implementation does not contain any try/catch or fallback logic around cache.get. Users relying on this generated example may write tests that assert nonexistent resilience behavior, creating a false sense of fault tolerance and potentially masking real error-handling gaps in production code.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.