ClawHub
Back to skill

Security audit

virtual-tryon-scorer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward virtual try-on image scoring guide with no executable code, persistence, or hidden data handling.

Install only if you are comfortable having the agent analyze uploaded try-on photos, including face and body consistency. Expect the report format to be in Chinese unless you separately ask the agent to adapt the language.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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 (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The markdown instructs the model to present the evaluation in an exact structure whose headings and labels are entirely in Chinese. This is a natural-language locale constraint that does not provide user opt-in or explain why Chinese output is required, which can violate language/locale policy expectations.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.