Back to skill

Security audit

Image Analysis Litiao

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple image-analysis helper that uses the browser to open image links and does not include hidden code, persistence, or unrelated access.

Install this if you want a browser-based image analysis helper and are comfortable with it opening image URLs. Be cautious with private or untrusted links because loading them may reveal normal network metadata to the image host, and the documentation is currently Chinese-only.

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
  • 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)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The natural-language instructions and headings are presented exclusively in Chinese, which can force a specific language on users without opt-in. The file does not indicate that the skill is region-specific or provide an alternative language option.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The skill explicitly tells the agent to open externally provided image URLs in a browser, which can trigger outbound network requests to third-party infrastructure and expose metadata such as IP, headers, or timing. In the context of images received from QQ or other untrusted sources, this also increases SSRF-like and privacy risks unless the user is clearly warned and link handling is constrained.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.