ClawHub
Back to skill

Security audit

Publish Skill

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward image-generation instruction file that discloses its use of user-provided API keys and external image providers.

Before installing, users should understand that generated-image requests may be routed to whichever configured provider API key is available, in the documented priority order. Use API keys you control and avoid sending sensitive text in image prompts.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The skill description says it should be used whenever a user needs image generation or AI drawing, which is very broad and lacks narrow activation criteria. In an agent environment, this can cause over-triggering on loosely related requests, increasing the chance that the skill is invoked unexpectedly and gains access to user prompts or configured API-backed capabilities when a more specific tool should have been selected.

Vague Triggers

Medium
Confidence
89% confidence
Finding
The example trigger phrases are ordinary conversational requests like '帮我生成…' and '画一幅…', which are common enough to overlap with broader assistant behavior and may not reliably distinguish when this specific skill should be selected. This ambiguity raises the risk of unintended invocation, especially because the skill can route requests to external image-generation providers using user-configured API keys.

Static analysis

No suspicious patterns detected.