ClawHub
Back to skill

Security audit

SocQ TikTok Shop Research

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed SocQ integration for public TikTok Shop research, with normal API-key and paid-API risks plus an unpinned CLI fallback to consider.

Install only if you are comfortable giving SocQ an API key and sending your TikTok Shop research inputs to SocQ’s hosted service. Consider pinning or preinstalling a trusted @socq/cli version instead of relying on npx latest, and use API-key limits or allowlists for cost and credential control.

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)

Rp1

Medium
Category
MCP Rug Pull
Confidence
85% confidence
Finding
The skill permits execution via `npx` without pinning an exact package version, which creates a supply-chain risk: a future malicious or compromised release of `@socq/cli` could be fetched and run at execution time. In an agent skill context, this is more dangerous because installation/execution may happen automatically and can expose environment secrets such as `SOCQ_API_KEY` or run attacker-controlled code.

Rp1

Medium
Category
MCP Rug Pull
Confidence
95% confidence
Finding
The command `npx @socq/cli` pulls and executes the latest published package unless a version is pinned, enabling remote code execution through a compromised dependency or malicious upstream release. Because this skill explicitly relies on an API key in the environment, an attacker-controlled package could exfiltrate credentials or tamper with collected data.

External Transmission

Medium
Category
Data Exfiltration
Content
value: "socq"
      description: "Hosted SocQ TikTok Shop data tools"
      transport: "streamable_http"
      url: "https://api.socq.ai/mcp?platforms=tiktok-shop"
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
value: "socq"
      description: "Hosted SocQ TikTok Shop data tools"
      transport: "streamable_http"
      url: "https://api.socq.ai/mcp?platforms=tiktok-shop"
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
SKILL.md:32