ClawHub
Back to skill

Security audit

Raphael Ai Image

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Raphael AI image-generation workflow that uses browser automation, saves generated images locally, and sends them to Discord as part of its stated purpose.

Install only if you are comfortable with prompts and generated images being sent to Raphael AI, saved locally under the OpenClaw media workspace, and posted to the current Discord channel. Delete saved media manually if you do not want it retained.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger examples are broad natural-language requests like '帮我生成一张奇幻风格的森林图', which can cause the skill to activate on ordinary conversation without clear user awareness that browser automation, local file download, and Discord upload will occur. In this skill’s context, that increases the chance of unintended execution and content handling rather than direct code execution, but it still creates privacy, consent, and misuse risks.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly states it will extract an image URL, download the file locally, and then send it to Discord, but it does not warn users that generated images will be stored under a local workspace path first. This omission matters because prompts or generated media may be sensitive, and local persistence plus reposting to Discord expands exposure if users assume the action is transient.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The natural-language instructions and examples direct users and sub-agents to invoke the skill using Chinese phrases such as "生成一张..." and "帮我生成一张奇幻风格的森林图," with no opt-in or alternative locale guidance. This creates a language-policy concern because the skill appears to require a specific language for use rather than offering user choice.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.