ClawHub
Back to skill

Security audit

gpt-multimodal

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward OpenAI vision-analysis guide, with expected API use and no hidden execution or persistence behavior found.

Before using this skill, treat any submitted image, image URL, prompt, and extracted text as data sent to the OpenAI API. Avoid confidential screenshots, personal documents, regulated data, or secrets unless you have approval, and keep OPENAI_API_KEY in secure environment configuration rather than code or logs.

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
  • 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
96% confidence
Finding

The skill encourages users to submit local images, image URLs, and OCR-style extraction tasks to the OpenAI API, but it does not clearly disclose that image contents and any extracted text are sent to an external third-party service. This can lead to unintentional exfiltration of sensitive visual data such as IDs, receipts, whiteboards, screenshots, or documents, especially because the skill is framed as a general-purpose analysis tool.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The examples instantiate the client with OPENAI_API_KEY from the environment, but the skill does not explicitly warn users that the integration depends on that credential being present and protected. While reading an API key from an environment variable is standard practice, omission of this warning can still cause unsafe handling, such as users pasting keys into code, prompts, or logs while troubleshooting.

Content

No source excerpt is available for this finding.