Back to skill

Security audit

DataXAPI Bilibili

Security checks for vulnerabilities and agentic risk

Overview

This skill provides clearly disclosed, paid access to public Bilibili data, with manageable privacy and installation risks.

Send only necessary, non-sensitive search terms, keep the API key secret, and set spending limits. Prefer REST or hosted MCP, or review and pin the CLI version. This review covers the supplied instructions; the external service and npm package remain unaudited.

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: "bilibili" 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":"bilibili.videos.search","query":"机械键盘","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/bilibili/videos/search" \
  --data-urlencode "query=机械键盘" \
  -H "Authorization: Bearer $DATAXAPI_API_KEY"

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

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The documented npx dataxapi and global installation commands do not pin a package version, allowing newly published package code to execute locally. A compromised release could access the DataXAPI key and other resources available to the agent; this is a dependency supply-chain risk, not evidence that the package is malicious or that an MCP server version is missing.

Content

No source excerpt is available for this finding.

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

Medium
Category
Output Handling
Confidence
93% confidence
Finding

The fallback explicitly directs the agent to send the user's words to an external discovery service without requiring extraction of only the necessary search intent. Although external queries are expected for this skill, forwarding wording verbatim could disclose private context or secrets that are unnecessary for endpoint discovery; the skill does not show that any such disclosure has actually occurred.

Content

No source excerpt is available for this finding.