Back to skill

Security audit

DataXAPI Wechat

Security checks for vulnerabilities and agentic risk

Overview

The skill provides clearly disclosed, paid WeChat searches with proportionate access and spending controls.

DataXAPI receives your search and discovery terms, so remove confidential details. Set spending limits; empty searches and additional pages incur charges. Prefer REST/MCP or a reviewed, pinned CLI version. The remote service and CLI implementation are outside this artifact review.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 · SKILL.md (reported line 27)May include surrounding context.

Call it three ways

MCP. Server https://api.dataxapi.com/mcp, header Authorization: Bearer <key>. Tools: find (with platform: "wechat" it lists this platform's endpoints), describe (parameters and price), call, read_more (free), account (balance). Setting the server up: https://dataxapi.com/agents.md

json
{"capability":"wechat.posts.search","query":"咖啡店开业","max_price":"0.02"}

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 · SKILL.md (reported line 42)May include surrounding context.

REST:

bash
curl -G "https://api.dataxapi.com/v1/wechat/posts/search" \
  --data-urlencode "query=咖啡店开业" \
  -H "Authorization: Bearer $DATAXAPI_API_KEY"

MCP server referenced without pinned version: 'npx dataxapi'.

Medium
Category
MCP Rug Pull
Confidence
91% confidence
Finding

The skill recommends executing an unpinned npm package through npx dataxapi or installing it globally without a version. A compromised future release could execute with the agent's permissions and access its environment, including the API key; this is a CLI supply-chain issue rather than an unpinned MCP server.

Content

No source excerpt is available for this finding.

The fallback workflow sends the user's words to DataXAPI without warning about third-party disclosure.

Medium
Category
Output Handling
Confidence
91% confidence
Finding

The fallback directs the agent to send the user's words to the external discovery service without requiring minimization or checking for sensitive content. Although third-party search is the skill's stated purpose, endpoint discovery generally needs only a capability description, so forwarding user wording can unnecessarily disclose personal or confidential details.

Content

No source excerpt is available for this finding.