ClawHub
Back to skill

Security audit

抖音数据分析 SocialDataX 作品详情

Security checks for vulnerabilities and agentic risk

Overview

The skill’s instructions fit Douyin content research, with disclosed API-key use and optional media downloads.

CLI use runs external software with your agent’s permissions and uses a potentially billable API. Prefer a reviewed, pinned package version or a trusted existing MCP connection. Keep the API key local and out of version control, and choose download destinations explicitly. This review covered the complete bundled artifact, but did not verify the external CLI implementation or hosted service.

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
  • 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 (4)

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

Medium
Category
MCP Rug Pull
Confidence
98% confidence
Finding

The command executes socialdatax-skills@latest through npx -y, automatically accepting execution of a mutable package version rather than a reviewed release. Although this is a direct CLI rather than an MCP server, a compromised future release could execute with the agent's permissions and access its API key and other accessible local data; the read-only API workflow does not restrict local package execution.

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
98% confidence
Finding

The URL-based detail command also executes socialdatax-skills@latest using npx -y, leaving the executed version subject to changes in the registry's latest tag. This repeats the same supply-chain exposure as the ID-based command: a compromised release could access credentials and files available to the agent, despite the intended read-only operation.

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
98% confidence
Finding

The media-saving guidance introduces another execution of socialdatax-skills@latest through npx -y, so a mutable, potentially unreviewed release runs locally. Not requiring an API key for this operation reduces its functional credential needs but does not prevent malicious package code from reading inherited secrets or modifying files accessible to the agent.

Content

No source excerpt is available for this finding.

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

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.