Back to skill

Security audit

DataXAPI Zhihu

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently retrieves public Zhihu data through a disclosed paid service, with routine privacy and installation precautions.

DataXAPI receives your lookup terms and charges for calls, including additional pages and some empty results. Keep sensitive details out of discovery queries and set a spending limit. Prefer the documented REST or MCP route, or review and pin the CLI version before installing it. This review covers the supplied instructions, not the live service or external package 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: "zhihu" 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":"zhihu.trends.list","max_price":"0.002"}

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

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The suggested npx dataxapi invocation can download and execute an unpinned package version; the global installation alternative is also unpinned. A compromised package release could execute with the agent process's permissions and access its credentials, including DATAXAPI_API_KEY, although no compromised release is demonstrated here.

Content

No source excerpt is available for this finding.

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

The fallback lookup sends the user's words to DataXAPI without a privacy disclosure.

Medium
Category
Output Handling
Confidence
93% confidence
Finding

The workflow explicitly instructs the agent to run find with the user's words, transmitting user-provided text to a third-party service. Although the skill describes DataXAPI and its pricing, it does not warn that the user's request text is shared for endpoint discovery.

Content

No source excerpt is available for this finding.