Back to skill

Security audit

Styrene

Security checks for vulnerabilities and agentic risk

Overview

The skill is not clearly malicious, but its stated styrene-distillation purpose does not match its gear/mechanical ordering workflow and it sends user parameters to an unauthenticated external service.

Review before installing. Use this only if you intend to send engineering parameters to jixietools.com and are comfortable with unauthenticated guest links/codes being used to access job status and outputs. The publisher should fix the styrene-versus-gear/category mismatch, add clear privacy and bearer-link warnings, and replace shell interpolation examples with safe structured request construction.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Error
Location
SKILL.md:90
Finding

Shell Command Injection Through Unsafe JSON Interpolation

Content
View full analysis
Remediation
View remediation
"$payload_file" curl --fail-with-body --silent --show-error \ -X POST "https://jixietools.com/api/v1/products/${PRODUCT_ID}/calculate" \ -H "Content-Type: application/json" \ --data-binary "@$payload_file" ``` Before using this pattern, `PRODUCT_ID` must still be strictly validate ...[truncated 134 chars]
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (12)

Description-Behavior Mismatch

High
Category
Not specified by scanner
Confidence
99% confidence
Finding

The skill claims to generate styrene-distillation CAD drawings, but the documented workflow actually interacts with a generic mechanical-product ordering API and production-sheet flow. This mismatch can mislead users and the hosting agent into sending requests and user inputs to an unrelated external service under false pretenses, creating both security and trust risks.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The file contains internal contradictions: it labels the skill as styrene-related while using gear/mechanical examples and conflicting category identifiers. Such inconsistencies are a strong indicator of copy-paste misconfiguration or deceptive packaging, which increases the chance that users will unknowingly trigger unintended external actions or receive unrelated outputs.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
90% confidence
Finding

Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

Content

Scanner excerpt · SKILL.md (reported line 29)May include surrounding context.

Step 1: 列出苯乙烯精馏工段产品

  1. 用 curl 获取苯乙烯精馏工段列表:
    bash
    curl -s "https://jixietools.com/api/v1/products?category_id=8" | python3 -m json.tool
    

External Script Fetching

High
Category
Supply Chain
Confidence
90% confidence
Finding

Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

Content

Scanner excerpt · SKILL.md (reported line 29)May include surrounding context.

Step 1: 列出苯乙烯精馏工段产品

  1. 用 curl 获取苯乙烯精馏工段列表:
    bash
    curl -s "https://jixietools.com/api/v1/products?category_id=8" | python3 -m json.tool
    

External Script Fetching

High
Category
Supply Chain
Confidence
90% confidence
Finding

Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

Content

Scanner excerpt · SKILL.md (reported line 47)May include surrounding context.

用户选择后,获取该产品的参数定义:

bash
curl -s "https://jixietools.com/api/v1/products/PRODUCT_ID/start" | python3 -m json.tool

返回结构:

External Script Fetching

High
Category
Supply Chain
Confidence
90% confidence
Finding

Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

Content

Scanner excerpt · SKILL.md (reported line 147)May include surrounding context.

  1. 收集要修改的参数名和新值
  2. 构建增量请求:只包含变化的参数 + filename:
    bash
    curl -s -X POST "https://jixietools.com/api/v1/products/PRODUCT_ID/calculate" \
      -H "Content-Type: application/json" \
      -d '{"inputs": {"修改的参数名": "新值"}, "filename": "之前保存的filename"}'
    

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger set includes broad activators such as a single English keyword, which can cause accidental invocation in unrelated conversations. In a skill that performs external network actions and creates remote jobs, unintended activation raises the risk of sending user data or initiating side effects without clear intent.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill instructs sending user-supplied parameters to an external service and emphasizes that job creation is unauthenticated, but it does not warn users that their inputs leave the system. This undermines informed consent and may expose proprietary engineering data or operational details to a third party.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
91% confidence
Finding

This step directs the agent to POST data to an external API to derive dropdown options, meaning user workflow data is transmitted off-platform before the full task is even confirmed. Even when the payload seems minimal, it still establishes an external side channel and normalizes network exfiltration without user notice.

Content

Scanner excerpt · SKILL.md (reported line 78)May include surrounding context.

  • 有 options_source 的参数(下拉选项类型): 先进行一次预计算获取 dropdown 选项:
    bash
    curl -s -X POST "https://jixietools.com/api/v1/products/PRODUCT_ID/calculate" \
      -H "Content-Type: application/json" \
      -d '{"inputs": {"有选项的参数名": ""}}'
    

External Transmission

Medium
Category
Data Exfiltration
Confidence
94% confidence
Finding

The incremental update flow sends modified parameters and a persistent filename token to an external service. This can expose sensitive engineering values and a reusable job reference that ties together a user's session history, increasing privacy and unauthorized-access risk if intercepted or mishandled.

Content

Scanner excerpt · SKILL.md (reported line 147)May include surrounding context.

  1. 收集要修改的参数名和新值
  2. 构建增量请求:只包含变化的参数 + filename:
    bash
    curl -s -X POST "https://jixietools.com/api/v1/products/PRODUCT_ID/calculate" \
      -H "Content-Type: application/json" \
      -d '{"inputs": {"修改的参数名": "新值"}, "filename": "之前保存的filename"}'
    

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill exposes guest URLs and codes for viewing job status and outputs without warning that possession of those values may grant access. If these links are shared, logged, or surfaced in multi-user contexts, unauthorized parties may monitor progress or retrieve generated files.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
98% confidence
Finding

The instruction “用中文与用户对话” forces a specific language for all interactions. Under the policy, language constraints should either offer user opt-in or be clearly documented as a justified region- or compliance-specific requirement.

Content

No source excerpt is available for this finding.