Back to skill

Security audit

创客贴智能海报设计

Security checks for vulnerabilities and agentic risk

Overview

This skill openly sends a graphic-design prompt to Chuangkit to generate a poster thumbnail and opens the returned image, with no hidden persistence or local privilege behavior found.

Install only if you are comfortable sending design prompts to Chuangkit's external service and having the returned thumbnail opened in your browser. Avoid including confidential business plans, unreleased product details, personal data, or secrets in prompts unless that sharing is acceptable.

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
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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill description uses broad, common phrases such as '做海报', '设计', and 'Banner', which can cause the skill to trigger on ordinary conversation that only loosely relates to graphic design. Over-broad activation increases the chance of unintended external API calls and browser-opening behavior without the user clearly intending to invoke this specific skill.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill sends the user's raw design prompt to a third-party service without explicitly warning the user that their content will leave the local environment. Because design prompts may contain sensitive business plans, marketing copy, personal event details, or confidential product information, this creates a privacy and data-handling risk if users are unaware of the transmission.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.