Back to skill

Security audit

DataXAPI Products

Security checks for vulnerabilities and agentic risk

Overview

The skill performs a clearly disclosed, spending-capped product research task, with ordinary dependency-installation risks.

Expect paid calls after the agent announces the estimate. Check the spending cap, use a budget-limited API key, and prefer a reviewed, pinned CLI version. Protect the resulting CSV because it contains review text and reviewer identifiers. This review covers the skill instructions, not the external CLI implementation.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

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

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

Although this is a CLI rather than an MCP server, npx dataxapi can download and execute an unpinned package version; the alternative npm install -g dataxapi has the same version-selection weakness. A compromised upstream release could execute with the agent's permissions and access DATAXAPI_API_KEY, local files, or other credentials. The spending caps and treatment of review text as untrusted are useful safeguards, but do not constrain malicious package code.

Content

No source excerpt is available for this finding.