Back to skill

Security audit

DataXAPI

Security checks for vulnerabilities and agentic risk

Overview

The skill coherently documents paid public-data retrieval, with disclosed options for saving credentials and configuring local agents.

Use a reviewed, pinned CLI version and a spending-limited API key. Review prices and set call or run budgets. If using setup, select the intended client explicitly and prefer environment credentials over copying keys into configurations. This review covers the bundled instructions; external CLI behavior and credential-file protections 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

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

Medium
Category
MCP Rug Pull
Confidence
92% confidence
Finding

The skill recommends executing an unpinned npm package through npx dataxapi or installing it globally without a version constraint. Although this line is a CLI fallback rather than an explicit MCP server configuration, a compromised future package release could execute with the agent's permissions and access credentials such as DATAXAPI_API_KEY; the document alone does not establish that any release is malicious.

Content

No source excerpt is available for this finding.

The documented setup capability modifies other AI agents' configurations, beyond retrieving public platform data.

Medium
Category
Excessive Agency
Confidence
93% confidence
Finding

L122–L126 expose a setup command that installs an MCP server and base skill into local coding agents, defaults to agents discovered under the home directory, and can write an API key into their configuration files. Reconfiguring other agents and persisting credentials in their configurations is a distinct machine-configuration capability, not required by the manifest's stated find/price/call data-retrieval workflow.

Content

No source excerpt is available for this finding.