Back to skill

Security audit

DataXAPI Viral

Security checks for vulnerabilities and agentic risk

Overview

The skill retrieves one social post through a disclosed paid service, with bounded spending and no apparent hidden behavior.

Use a trusted, preferably pinned DataXAPI CLI version. Configure only the required service key and check the previewed spending cap before paid calls. Requested post identifiers go to DataXAPI. The reference gaps were investigated, but the external CLI’s implementation and enforcement of its advertised limits remain outside this artifact review.

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
95% confidence
Finding

Although the referenced package is a CLI rather than an MCP server, npx dataxapi can download and execute an unpinned package version; the alternative npm install -g dataxapi is also unpinned. A compromised package release could execute code with the agent's permissions and access available files or credentials, including DATAXAPI_API_KEY when configured. The package serves a legitimate task, and the skill explicitly treats fetched content as untrusted, but that safeguard does not protect against compromised executable dependencies.

Content

No source excerpt is available for this finding.