Back to skill

Security audit

Persona Project Manager

Security checks for vulnerabilities and agentic risk

Overview

This is a simple project-management persona skill that uses Google Workspace tools in ways that match its stated purpose, with some ordinary sharing risk users should control.

Install this if you want a Google Workspace project-management persona, but review dry-run previews and confirm recipients, attendees, uploaded files, and sharing permissions before allowing emails, calendar invites, Drive uploads, or announcements.

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
Confidence
86% confidence
Finding
The skill directs the agent to send emails, upload files to Drive, and announce/share artifacts, but it does not require explicit user confirmation, data-classification checks, or warnings about external transmission. In a persona skill centered on project coordination, these actions are plausible, but the lack of guardrails increases the risk of unintended disclosure of sensitive documents, stakeholder information, or meeting details.

Static analysis

No suspicious patterns detected.