ClawHub
Back to skill

Security audit

SearchDock Setup

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed setup helper for SearchDock and read-only Google Search Console access, with a supply-chain caution around one unpinned installer command.

Before installing, be aware that this skill can install CLI tooling, add skills, update MCP configuration, and create local OAuth credentials for read-only Search Console access. Prefer project-scoped setup, verify the npm packages and repository source, and do not share OAuth client JSON, tokens, or private report output.

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
  • 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 (1)

Rp1

Medium
Category
MCP Rug Pull
Confidence
90% confidence
Finding

The skill instructs the agent to execute npx --yes skills add ... without pinning the skills package to an exact version. This allows whatever version is currently published under that package name to run at install time, creating a supply-chain risk if the package is updated maliciously, compromised, or behaves incompatibly. Because this skill is specifically about installing tooling and modifying agent configuration, the execution context makes the risk more meaningful than a purely informational reference.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.