Back to skill

Security audit

The Style Index

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Style Index wardrobe and virtual try-on integration, with sensitive photo handling that is expected for the feature but worth reviewing before use.

Before installing, be comfortable sharing your email, clothing photos, and a full-body reference photo with The Style Index. Treat the agent key as sensitive and use account settings to revoke access if you no longer want the agent connected.

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
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • 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)

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
80% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · SKILL.md (reported line 103)May include surrounding context.

Delete items:

text
DELETE /api/agent/wardrobe/<item_id>

2. Get Outfit Suggestions

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill explicitly asks for a full-body photo for virtual try-on, which is sensitive image data and may enable biometric-style inference or highly personal profiling. Although the skill includes a general consent flow earlier, it does not give a clear, user-facing warning at the point of collection about the sensitivity of the photo, what processing will occur, retention expectations, or how the image will be used, increasing privacy risk and reducing informed consent.

Content

No source excerpt is available for this finding.