ClawHub
Back to skill

Security audit

SocQ LinkedIn Research

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed SocQ integration for public LinkedIn research, with expected external API use and no artifact-backed hidden or destructive behavior.

Install only if you intend to use SocQ for LinkedIn research and are comfortable sending requested public LinkedIn queries plus your SocQ API-authenticated requests to SocQ. Prefer a vetted or pinned @socq/cli version where possible, keep SOCQ_API_KEY in the environment, and confirm costs before broad paid collections.

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
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.

Rp1

Medium
Category
MCP Rug Pull
Confidence
86% confidence
Finding
The skill explicitly recommends `npx @socq/cli` without pinning a version, which can cause an agent to fetch and execute the latest published package at runtime. If the package is compromised, typosquatted, or a malicious version is published, this creates a supply-chain execution risk on the host running the agent.

External Transmission

Medium
Category
Data Exfiltration
Content
value: "socq"
      description: "Hosted SocQ LinkedIn data tools"
      transport: "streamable_http"
      url: "https://api.socq.ai/mcp?platforms=linkedin"
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 LinkedIn data tools"
      transport: "streamable_http"
      url: "https://api.socq.ai/mcp?platforms=linkedin"
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