Back to skill

Security audit

抖音商品竞品对比

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent read-only Douyin product comparison helper, but it runs an unpinned npm package at invocation time, so the executable code can change after review.

Review this before installing if you require reproducible or tightly controlled execution. The skill appears read-only and scoped to Douyin product details, but it should ideally pin `socialdatax-skills` to a reviewed exact version and run only in an environment where exposing `SOCIALDATAX_API_KEY` to that CLI is acceptable.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Rp1

Medium
Category
MCP Rug Pull
Confidence
96% confidence
Finding

The skill instructs agents to execute npx -y socialdatax-skills@latest ..., which fetches and runs whatever code is currently published under that package at execution time. Because the version is not pinned and uses @latest, a compromised publisher account, malicious update, or supply-chain takeover could cause arbitrary code execution in the agent environment.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
96% confidence
Finding

This command also uses npx -y socialdatax-skills@latest, creating the same unpinned remote-code-execution risk each time the skill is invoked. In agent environments, this is especially dangerous because the fetched package executes with the agent's local permissions and may access environment variables such as SOCIALDATAX_API_KEY.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.