ClawHub
Back to skill

Security audit

Recipe Email Drive Link

Security checks for vulnerabilities and agentic risk

Overview

This is a simple recipe for sharing a Google Drive file and emailing its link, with the main risk being ordinary accidental oversharing.

Before using this recipe, confirm the Drive file is approved to share externally, replace the example recipient with the intended address, and verify the recipient and permission before sending the email.

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 (1)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill operationalizes sharing a Google Drive file with an external recipient and then emailing the access link, but it does not include any warning, consent check, recipient validation, or guidance about sensitivity of the file. This creates a real data-disclosure risk because a user may run the recipe on confidential content and unintentionally grant external access and distribute the link.

Static analysis

No suspicious patterns detected.