ClawHub
Back to skill

Security audit

Google Calendar

Security checks for vulnerabilities and agentic risk

Overview

This Google Calendar skill is mostly coherent, but its first-time setup tells an agent to run a remote installer script without verification or clear user approval.

Before installing, review the OOMOL CLI installer source or use a safer verified installation method if available. Do not let the agent run write or destructive Google Calendar actions unless it shows the exact target, payload, and effect and you explicitly approve them.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

External Script Fetching

High
Category
Supply Chain
Confidence
96% confidence
Finding

The skill instructs the agent to install software using a remote script piped directly into a shell, which executes unreviewed code fetched at runtime. If the host, transport, or distribution pipeline is compromised, this can lead to arbitrary code execution on the user's machine under the current user's privileges.

Content

Scanner excerpt · SKILL.md (reported line 92)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The instruction to use this skill for ANY Google Calendar request is overly broad and can cause the agent to route all calendar-related tasks through this skill without sufficient narrowing or user-intent checks. In contexts involving write or destructive actions, this increases the chance of unintended state-changing operations being selected or prioritized when a more constrained path would be safer.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.