Back to skill

Security audit

DataXAPI Account Audit

Security checks for vulnerabilities and agentic risk

Overview

The skill coherently describes a limited, paid account-reporting workflow, with ordinary external-package risks.

Use your intended platform and account, check the current plan and spending cap before execution, and keep the API key private. Prefer a reviewed, pinned CLI version. This review covers the supplied instructions; the external npm package and service 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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
88% confidence
Finding

The command targets the relevant account-audit workflow, but the supplied chunk does not implement the declared user-directed retrieval: it specifies a fixed account and requests a plan. No unrelated access or malicious behavior is evident. The interpretation of --plan assumes its conventional planning-only meaning; the CLI implementation is not supplied.

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 fallback npx dataxapi and the global installation command resolve an unpinned package version, creating a supply-chain risk if a future release or the package distribution is compromised. Although this is a CLI rather than an MCP server, the underlying concern applies: downloaded code runs with the agent's permissions and may have access to DATAXAPI_API_KEY and local files. Nothing in the supplied content establishes that the package is currently malicious.

Content

No source excerpt is available for this finding.