Back to skill

Security audit

DataXAPI Facebook

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently retrieves public Facebook data through a disclosed paid service, with manageable privacy and installation caveats.

DataXAPI receives your requested identifiers and discovery queries, and calls spend prepaid credit. Use minimal discovery terms, keep confidential context out, and set a spending limit. Prefer REST, hosted MCP or a reviewed, pinned CLI version. The external package and service implementation were not audited.

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: "facebook" 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":"facebook.pages.posts.list","id":"100044561550831","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/facebook/pages/posts/list" \
  --data-urlencode "id=100044561550831" \
  -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 with the agent's permissions. Although this is a CLI dependency rather than an MCP server version, a compromised release could access the API key or other resources available to the process; there is no evidence that the package is currently malicious.

Content

No source excerpt is available for this finding.

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

Medium
Category
Output Handling
Confidence
90% confidence
Finding

The fallback explicitly directs the agent to send the user's words to an external discovery service without requiring minimization or checking for sensitive content. Facebook endpoint discovery generally needs only a short capability description, so forwarding the original wording could unnecessarily disclose private context, although the actual exposure depends on what the user supplied.

Content

No source excerpt is available for this finding.