ClawHub
Back to skill

Security audit

Recipe Post Mortem Setup

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Google Workspace recipe for creating a post-mortem document, calendar event, and chat notice, with no hidden or unrelated behavior found.

Before installing or running, confirm the incident name, document contents, calendar attendees, meeting time, and Chat space. This recipe writes to Google Workspace and may expose incident details to the selected recipients, but no hidden execution or unrelated access was found.

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
Category
Not specified by scanner
Confidence
87% confidence
Finding

This recipe creates a Google Doc, schedules a calendar event, and sends a Chat notification, but it does not warn the user that it will create and distribute potentially sensitive incident information across Google Workspace services. In an engineering post-mortem context, incident names, timelines, root causes, and attendee lists may expose internal operational details, so lack of explicit warning and consent increases the risk of unintended disclosure.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.