ClawHub
Back to skill

Security audit

Google SERP Maps Places API

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrow Just Serp API wrapper for Google Maps place details, with a minor credential-handling caution but no hidden or destructive behavior found.

Install only if you are comfortable giving the skill a Just Serp API key and allowing it to call the documented Just Serp endpoint. Prefer rotating the key if it has been used in environments that log process arguments, and avoid running with shell tracing or command auditing that records secrets.

A.I.G

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Note
Location
bin/run.mjs:157
Finding

API Key Exposed Through Process Command-Line Arguments

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
84% confidence
Finding

The skill invokes a network-capable helper (node .../run.mjs) but does not declare an explicit tool scope such as permissions or allowed-tools. This creates a governance gap: an agent platform may permit broader execution or fail to clearly constrain/communicate that the skill performs outbound API calls using a secret-backed credential, increasing the chance of unintended external requests or misuse.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.