Back to skill

Security audit

DataXAPI Instagram

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently retrieves public Instagram data through a disclosed paid provider, with ordinary privacy and software dependency precautions.

Use an Instagram-scoped provider key with a spending limit, and send only necessary identifiers or generic discovery terms. DataXAPI states that call parameters are retained for 30 days in its [privacy policy](https://dataxapi.com/privacy/). Prefer REST or a reviewed, pinned CLI version. The complete bundled instructions were inspected, but external package code and hosted service behavior were not verified.

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: "instagram" 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":"instagram.users.get","username":"nasa","max_price":"0.002"}

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

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The skill recommends running or globally installing the dataxapi npm package without pinning a version. This exposes the agent environment to changing executable dependencies: a compromised future release could access the API key and other resources available to the process. The finding concerns CLI package execution, not an unversioned MCP server implementation.

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/instagram/users/get" \
  --data-urlencode "username=nasa" \
  -H "Authorization: Bearer $DATAXAPI_API_KEY"

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

Medium
Category
Output Handling
Confidence
91% confidence
Finding

The fallback explicitly directs the agent to use the user's words for third-party endpoint discovery without requiring minimization or sensitive-data filtering. Those words could contain confidential context unrelated to selecting an Instagram endpoint. The skill clearly identifies DataXAPI as its provider, which reduces surprise, but does not establish permission to transmit unnecessary portions of a request.

Content

No source excerpt is available for this finding.