Back to skill

Security audit

DataXAPI Linkedin

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently retrieves public LinkedIn data through DataXAPI, with ordinary third-party privacy, cost, and software-dependency cautions.

DataXAPI receives lookup terms and uses your prepaid balance. Keep confidential context out of discovery queries and set a spending limit. Prefer REST or remote MCP, or review and pin the CLI version before installing it. This review covers the bundled instructions; external package code and service-side behavior remain unverified.

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: "linkedin" 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":"linkedin.companies.posts.list","username":"unesco","max_price":"0.002"}

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

Medium
Category
MCP Rug Pull
Confidence
92% confidence
Finding

The suggested npx dataxapi invocation can download and execute an unpinned npm package with the agent's local permissions. A compromised future release could access the API key and other accessible local data; this is a supply-chain exposure, not evidence that the package is currently malicious.

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/linkedin/companies/posts/list" \
  --data-urlencode "username=unesco" \
  -H "Authorization: Bearer $DATAXAPI_API_KEY"

The fallback discovery step sends the user's words to DataXAPI without warning that their query text will be shared with a third party.

Medium
Category
Output Handling
Confidence
91% confidence
Finding

The fallback directs the agent to use the user's words for discovery without requiring minimization or checking for sensitive information. Although third-party API use is central to this skill, forwarding the original wording can unnecessarily disclose private context beyond the public LinkedIn identifiers or search terms needed for the task.

Content

No source excerpt is available for this finding.