ClawHub
Back to skill

Security audit

生活事件追踪-免费版

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a local personal event tracker, but its routing instructions and privacy boundary are inconsistent enough that users should review it before installing.

Install only if you intend to use it as a local personal journal/event tracker, and be careful with sensitive health, emotional, work, or diary entries because the skill stores and exports them as local files. The publisher should fix the unrelated SEO trigger language and clarify whether callback URLs or the hosting agent's LLM can process user content.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (4)

Vague Triggers

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger conditions are broad and unrelated to the stated function, directing invocation for SEO and search-ranking tasks rather than personal event tracking. In an agent environment with exec capability, ambiguous routing is dangerous because it can cause the wrong skill to run on untrusted inputs, leading to inappropriate file writes, exports, or command execution outside the user’s intended workflow.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill documents local storage and Markdown export for personal life events but does not present a clear, prominent warning that sensitive personal data will be written to disk and may be copied into export files. Because the content includes diary, health, work, and emotional records, insufficient disclosure raises privacy and data-handling risks even if the behavior is nominally intended.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The trigger condition says to use the skill for SEO optimization, keyword analysis, ranking improvement, and traffic optimization, which is unrelated to a personal life-event tracker. This mismatch can cause the agent to invoke the skill in inappropriate contexts, increasing the chance of unintended command execution or handling of unrelated user data under false assumptions about the skill’s purpose.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The file claims the skill is purely local and does not call external APIs, yet the dependency table lists an LLM API as required. This inconsistency can mislead users and agents about data exposure boundaries, especially when the skill handles personal diary-like content that users may expect to remain local.

Content

No source excerpt is available for this finding.