ClawHub
Back to skill

Security audit

google-drive

Security checks for vulnerabilities and agentic risk

Overview

This is a clearly documented Google Drive integration that uses managed OAuth and discloses its write, credential, and automation risks.

Install only if you are comfortable authorizing Maton to access the selected Google Drive account. Prefer OAuth login over API keys, confirm the exact account and file IDs before writes, and treat sharing, deletion, hosted functions, triggers, and destinations as separate high-impact actions that need explicit approval and later cleanup when no longer needed.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The manifest says this skill is for Google Drive operations and explicitly states Google Drive is not an event source; however, this file documents Gmail-triggered email events and forwarding behavior. Even though the file notes it is shared platform reference text, bundling Gmail event capabilities into a Google Drive skill's materials creates a semantic mismatch between the skill's stated scope and what its documentation presents.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.