Back to skill

Security audit

yoooclaw-world-cup-post-match-review-scene

Security checks for vulnerabilities and agentic risk

Overview

This skill has a coherent sports-review purpose, but it can broadly read local notifications and group-chat/app message signals without a clear opt-in or tight scope.

Install only if you are comfortable with the agent using local notification/message-search capabilities for match discussion. Before running hot-topic or full-review requests, specify exact apps, groups, and time ranges, and avoid using it where unrelated private or work notifications may be included.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill instructs the agent to query local notifications, group chats, and app messages to extract fan discussion, with broad defaults such as searching from two hours before the match to 24 hours after. There is no clear user-facing consent, just-in-time privacy notice, or data-minimization gate before accessing potentially sensitive personal communications. In this context, the risk is elevated because group chats and notifications can contain unrelated private content, third-party data, and sensitive metadata beyond what the user expected to share.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill description defines broad activation triggers such as asking for a one-line match summary, how a match was played, who performed best, or hot post-match topics. These intents are common in ordinary sports conversation, so the skill may auto-invoke in situations where the user did not clearly intend to activate a tool with retrieval and notification-analysis behavior. That increases the chance of unexpected data access or surprise tool execution, especially because the skill also performs message/notification querying in some branches.

Content

No source excerpt is available for this finding.