ClawHub
Back to skill

Security audit

小红书博主数据 SocialDataX 博主信息

Security checks for vulnerabilities and agentic risk

Overview

The skill fits its profile-lookup purpose, with routine cautions about downloaded software, API credentials, and sending lookup inputs to SocialDataX.

Send only the profile ID or link needed for the lookup. Keep your API key out of chat and version control. Prefer a reviewed, pinned CLI version. The external CLI implementation was unavailable for inspection, so its actual behavior and future releases are outside this review.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

MCP server referenced without pinned version: 'npx -y socialdatax-skills'.

Medium
Category
MCP Rug Pull
Confidence
99% confidence
Finding

The command uses npx -y socialdatax-skills@latest, which automatically executes a mutable package version without an approval prompt. A compromised publisher account or malicious release could execute code with the agent process's permissions, including access to the API key and accessible workspace files; the documented read-only API behavior does not constrain package execution.

Content

No source excerpt is available for this finding.

Profile lookup instructions lack disclosure that user-supplied identifiers or share text are sent to SocialDataX.

Medium
Category
Output Handling
Confidence
87% confidence
Finding

The workflow instructs the agent to invoke SocialDataX with a creator ID or a profile URL/share text supplied by the user. Although the skill describes API authentication and calls itself read-only, it does not disclose that these inputs are transmitted to a third-party service; read-only operation does not eliminate this privacy consideration.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx -y socialdatax-skills'.

Medium
Category
MCP Rug Pull
Confidence
99% confidence
Finding

The profile-URL command also executes socialdatax-skills@latest through npx -y, exposing it to the same mutable-dependency supply-chain risk. Although this is a direct CLI rather than an MCP server, a malicious package release could access credentials or modify local files before performing any profile lookup.

Content

No source excerpt is available for this finding.