Back to skill

Security audit

Recipe Share Doc And Notify

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward Google Workspace recipe for sharing a document and emailing a collaborator, with no hidden code or persistence found.

Before using this skill, confirm the exact Google Doc, recipient email address, and permission level. Use viewer or commenter access instead of writer access unless editing is required.

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
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
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill performs two sensitive actions: granting edit access to a Google Doc and sending an email notification to an external collaborator, but it provides no explicit warning or confirmation guidance to the user. In a productivity context, this can lead to unintended data disclosure, unauthorized document modification, and accidental outreach if the document, recipient, or sharing scope is incorrect.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.