Back to skill

Security audit

google-search

Security checks for vulnerabilities and agentic risk

Overview

This Google search skill is purpose-aligned, but its error handling can expose the user's Google API key and search details in logs or agent output.

Review before installing. Use a restricted Google API key, avoid sensitive searches, and be aware that failed API calls may print credential-bearing request details until the script sanitizes errors and adds safer exception handling.

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

Warning
Location
scripts/search.py:8
Finding

Google API Key and Search Query Disclosure Through Unsanitized Exception Output

Content
View full analysis
Remediation
View remediation
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
91% confidence
Finding

The skill documents use of environment variables and outbound network access but does not declare any explicit tool scope such as permissions or allowed-tools. This creates a least-privilege and governance gap: an agent may invoke a skill with broader capabilities than reviewers or policy engines expect, increasing the chance of unauthorized secret access or external data exfiltration.

Content

No source excerpt is available for this finding.