Back to skill

Security audit

微博数据 API · Weibo data API · DataXAPI

Security checks for vulnerabilities and agentic risk

Overview

The scanners classify this Weibo data skill as suspicious because its discovery workflow may send users’ wording to an external service without disclosure, and its package installation instructions do not pin a version.

Before installing, consider whether you are comfortable with the discovery workflow sending your wording to DataXAPI and with installation commands that do not pin a package version. Avoid including sensitive details in discovery requests. The scan is partial: it inspected one Markdown component, but some local references could not be resolved, so the evidence is incomplete.

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)

The discovery workflow sends the user's words to DataXAPI without a user-facing disclosure.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

The fallback discovery instruction sends the user's words to an external service without requiring removal of unrelated sensitive information or a pre-transmission disclosure. DataXAPI use is explicit and relevant to the skill, which reduces suspicion, but forwarding user wording for endpoint discovery can expose more information than the subsequent API task requires.

Content

No source excerpt is available for this finding.

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

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The suggested npx dataxapi and global installation commands do not pin a package version, so installation can execute a newly published release rather than a reviewed artifact. A compromised release could execute code with the agent's permissions and access available credentials, although the file provides no evidence that the package is malicious; this is a package supply-chain issue, not an unversioned MCP server issue.

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 59)May include surrounding context.

dataxapi call weibo.trends.list --max-price 0.002

text

**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 68)May include surrounding context.

REST:

bash
curl -G "https://api.dataxapi.com/v1/weibo/trends/list" \
  -H "Authorization: Bearer $DATAXAPI_API_KEY"