ClawHub
Back to skill

Security audit

Get Today Connections

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple helper that fetches NYT Connections hints and answers from a third-party website, with no local code execution or persistence.

Install only if you are comfortable with the agent contacting connections-answers.com for current puzzle data. The source is not NYT, so users who need first-party accuracy or stronger privacy should verify results separately or avoid automatic fetching.

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

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger phrase includes the open-ended wording 'or similar questions', which can cause the skill to activate for requests beyond the narrowly intended NYT Connections use case. This is primarily a scope-control issue: ambiguous activation can lead to unintended tool use or incorrect routing, especially in systems where skill invocation causes external requests.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill directs the agent to fetch data from a third-party domain without any user-visible disclosure or consent flow. Even if the request is simple, invoking an external service can expose user intent, metadata, or usage patterns to that site, and normalizes silent outbound network access.

Content

No source excerpt is available for this finding.