Back to skill

Security audit

Yq Image Creator

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent image-generation skill with some privacy and routing caveats, but no evidence of hidden, persistent, destructive, or deceptive behavior.

Before installing, be aware that this skill may activate on broad image-adjacent terms and may process uploaded photos or product images through image analysis and generation tools. Avoid providing sensitive personal images unless you are comfortable with that processing.

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
94% confidence
Finding

The trigger list contains very broad terms such as 'figure', 'portrait', 'city', 'weather', and especially 'image generation/图像生成/图像创作', which are likely to match ordinary user conversation outside the skill’s intended scope. This can cause the skill to activate unexpectedly, intercept user requests, and route them into image-generation workflows the user did not explicitly choose, increasing the risk of inappropriate tool use and confusing or privacy-impacting behavior.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The workflow instructs the agent to send reference images to images_understand and prompts/images to gen_images, but the skill provides no user-facing notice that uploaded content may be transmitted to downstream tools or services. In an image-creation skill, users are especially likely to upload personal photos, so the missing disclosure meaningfully increases privacy and consent risk.

Content

No source excerpt is available for this finding.