Back to skill

Security audit

yoooclaw-family-digest

Security checks for vulnerabilities and agentic risk

Overview

The skill has a coherent family-notification summary purpose, but it can read sensitive phone notification files and has broad triggers that may run on less-specific requests.

Install only if you are comfortable letting the agent read local phone notification files for the requested date range and infer family relationships from names and message content. Use specific requests and avoid broad prompts if you do not want unrelated notifications reviewed.

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)

Vague Triggers

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill advertises many broad, everyday trigger phrases such as '今天的通知' and '重要信息', which are likely to match common conversation and cause the skill to activate unexpectedly. Because the skill reads and summarizes sensitive phone notifications, accidental invocation can expose private family communications beyond what the user specifically intended to access at that moment.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill is designed to process highly sensitive notification content, including messages from spouses, parents, and children’s teachers, but the markdown provides no explicit privacy notice, consent language, or minimization guidance to the user. In this context, users may not fully understand that broad notification history across multiple days and family members can be loaded and inferred, increasing the risk of overcollection and unintended disclosure.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.