ClawHub
Back to skill

Security audit

Aicloset Skill

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent AI Closet API documentation skill, but users should understand it sends wardrobe data, photos, and outfit context to the AI Closet service.

Install only if you trust the AI Closet service and are comfortable using an API key that accesses your bound account. Avoid submitting sensitive personal photos, location/date context, or images you are not authorized to share unless you understand the service's retention and privacy practices.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (16)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill handles wardrobe metadata and user photos via external API endpoints but does not warn users that personal images and lifestyle-related data will be transmitted to a third-party service. This creates a real privacy and consent issue because users may provide sensitive photos or personal preference data without understanding that the data leaves the local agent environment and is processed remotely.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The natural-language parameter description forces a binary gender choice by stating the value must be 男 or 女. This is a language/policy issue because it imposes a rigid demographic constraint without user opt-in, alternative options, or documented justification.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · api-ai.md (reported line 20)May include surrounding context.

请求示例

bash
curl -X POST https://aicloset-dev.wxbjq.top/skill/ai/outfit-recommend \
  -H "x-api-key: $AICLOSET_API_KEY" \
  -d "gender=女&occasion=约会&temperature=15℃～25℃&weather=晴"

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The parameter description requires gender and limits values to 男 or 女, which enforces a binary gender policy in the API contract. No opt-in, alternative values, or justification is provided in the documentation.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · api-ai.md (reported line 57)May include surrounding context.

请求示例

bash
curl -X POST https://aicloset-dev.wxbjq.top/skill/ai/kb-search \
  -H "x-api-key: $AICLOSET_API_KEY" \
  -d "query=白色连衣裙&gender=女&top_k=5"

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

This markdown file documents an image-processing endpoint that accepts a model image URL and generates a try-on result, which can involve personal or biometric-like user imagery. The description and example show the operation but provide no warning about privacy implications, external image transmission, or avoiding sensitive personal photos.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
69% confidence
Finding

The virtual try-on API accepts a user-supplied image URL, which can become dangerous if the backend server fetches that URL without strict validation. That pattern can enable SSRF, internal network probing, or fetching of sensitive resources, and the skill context increases risk because image-processing services commonly retrieve remote media server-side.

Content

Scanner excerpt · api-ai.md (reported line 98)May include surrounding context.

请求示例

bash
curl -X POST https://aicloset-dev.wxbjq.top/skill/ai/virtual-tryon \
  -H "x-api-key: $AICLOSET_API_KEY" \
  -d "garment_image=https://example.com/dress.jpg"

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · api-outfit.md (reported line 17)May include surrounding context.

请求示例

bash
curl -X POST https://aicloset-dev.wxbjq.top/skill/outfit/list \
  -H "x-api-key: $AICLOSET_API_KEY" \
  -d "page=1&page_size=10"

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The documentation instructs users to submit outfit photo URLs plus contextual metadata like date, city, weather, and temperature, but it provides no privacy notice, consent guidance, or warning that this personal data is sent to an external service. Because outfit photos and location/time context can reveal identity, habits, and whereabouts, this omission can lead to unintended disclosure of sensitive personal information.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
84% confidence
Finding

This endpoint sends a user's outfit photo reference and related metadata to an external domain, but the documentation does not warn about privacy implications or data sensitivity. In this skill context, OOTD photos combined with date and city can expose personal identity and behavioral patterns, making the transmission more sensitive than ordinary API traffic.

Content

Scanner excerpt · api-outfit.md (reported line 99)May include surrounding context.

请求示例

bash
curl -X POST https://aicloset-dev.wxbjq.top/skill/ootd/record-photo \
  -H "x-api-key: $AICLOSET_API_KEY" \
  -d "date=2026-03-23&image_url=https://example.com/ootd.jpg&city=北京&weather=晴"

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · api-outfit.md (reported line 136)May include surrounding context.

请求示例

bash
curl -X POST https://aicloset-dev.wxbjq.top/skill/ootd/record-outfit \
  -H "x-api-key: $AICLOSET_API_KEY" \
  -d "date=2026-03-23&outfit_id=5&city=北京&weather=晴"

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · api-wardrobe.md (reported line 17)May include surrounding context.

请求示例

bash
curl -X POST https://aicloset-dev.wxbjq.top/skill/wardrobe/list \
  -H "x-api-key: $AICLOSET_API_KEY" \
  -d "page=1&page_size=10"

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · api-wardrobe.md (reported line 60)May include surrounding context.

请求示例

bash
curl -X POST https://aicloset-dev.wxbjq.top/skill/wardrobe/create \
  -H "x-api-key: $AICLOSET_API_KEY" \
  -d "name=春季衣橱"

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The document describes uploading user images or providing image URLs to a remote API and explicitly states that AI processing occurs asynchronously, but it does not warn users that personal image data will be transmitted to and processed by an external service. Because clothing photos may contain sensitive personal information or embedded metadata, the lack of disclosure and consent guidance creates a real privacy/security risk.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
88% confidence
Finding

This example transmits user-supplied images or image URLs to a remote endpoint for AI processing, which materially increases privacy risk compared with ordinary metadata requests. The skill context makes this more dangerous because wardrobe photos can reveal a person's body, home environment, habits, and metadata, yet the documentation provides no caution, consent, or safe-handling guidance.

Content

Scanner excerpt · api-wardrobe.md (reported line 108)May include surrounding context.

请求示例（文件上传）

bash
curl -X POST https://aicloset-dev.wxbjq.top/skill/product/add \
  -H "x-api-key: $AICLOSET_API_KEY" \
  -F "image=@shirt.jpg" \
  -F "wardrobe_id=1"

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · api-wardrobe.md (reported line 153)May include surrounding context.

请求示例

bash
curl -X POST https://aicloset-dev.wxbjq.top/skill/product/edit \
  -H "x-api-key: $AICLOSET_API_KEY" \
  -d "product_id=100&name=白色T恤"