Back to skill

Security audit

DataXAPI Weibo

Security checks for vulnerabilities and agentic risk

Overview

The skill coherently provides paid access to public Weibo data, with ordinary privacy and installation considerations.

DataXAPI receives query terms and charges your prepaid balance for calls. Remove private context from discovery requests and set spending limits. Prefer REST or a reviewed, pinned CLI version. This review covers the instruction file, not the external package or live service implementation.

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: "weibo" 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":"weibo.trends.list","max_price":"0.002"}

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/weibo/trends/list" \
  -H "Authorization: Bearer $DATAXAPI_API_KEY"

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

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The recommended npx dataxapi and global installation commands do not pin a package version, allowing newly published package code to execute with the agent's permissions. A compromised release could access the API key or other accessible local data; this is a conditional supply-chain risk, not evidence that the package is currently malicious.

Content

No source excerpt is available for this finding.

The fallback endpoint-discovery workflow sends the user's words to DataXAPI without a privacy warning.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The fallback discovery instruction sends the user's words to an external provider without requiring minimization, potentially disclosing private context embedded in the request. Although external Weibo searches are part of the skill's advertised purpose, endpoint discovery generally needs only a generic capability description, not the user's original wording.

Content

No source excerpt is available for this finding.