Back to skill

Security audit

DataXAPI

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill suspicious because it uses unpinned package install commands and can make persistent changes to other agents' configurations; the scan was partial, so the evidence is incomplete.

Before installing, consider whether you trust the DataXAPI package publisher and are comfortable with its package being installed without a fixed version. Avoid sending private task details in discovery queries, and review any setup that changes other agents' configurations or stores an API key there. The scan covered the listed skill file but was marked partial because some local references could not be resolved, so it does not provide complete evidence about those references.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

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

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The fallback npx dataxapi and installation command npm install -g dataxapi do not specify a version, allowing newly published package code to execute without review. A compromised publisher account or malicious release could execute code with the agent's permissions and access available credentials, including DATAXAPI_API_KEY; this is a CLI supply-chain issue, not evidence of an unpinned MCP server specifically.

Content

No source excerpt is available for this finding.

The discovery workflow sends user-derived task text to DataXAPI without a privacy warning.

Medium
Category
Output Handling
Confidence
87% confidence
Finding

The workflow instructs the agent to find a capability using the user's own words, submitting that text to the third-party DataXAPI service. Although the skill explains pricing and public-data retrieval, it does not warn that discovery queries can disclose private task context or instruct the agent to remove sensitive information before submission.

Content

No source excerpt is available for this finding.

The skill exposes cross-agent configuration changes unrelated to retrieving platform data.

Medium
Category
Excessive Agency
Confidence
94% confidence
Finding

The setup command installs an MCP server and skill into other coding agents' configurations, defaults to agents discovered under the home directory, and can embed an API key in their MCP entries. These persistent changes to other agents are not necessary for the manifest's stated workflow of finding capabilities, checking prices, and fetching public platform data.

Content

No source excerpt is available for this finding.