Back to skill

Security audit

文本对比工具

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple text/file comparison helper with no hidden execution, persistence, network use, or unrelated data access.

Before installing, note that comparing files necessarily exposes the selected file contents to the agent performing the diff. Use explicit requests and avoid pointing it at sensitive files unless you intend their contents to be analyzed.

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)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The natural-language description, activation text, and section labels are presented in Chinese, and there is no indication that the user can choose another language or that the skill is intentionally limited to a Chinese-speaking context. This can violate language/locale policy when a skill imposes a language without opt-in.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The activation phrase list is broad enough to match common conversational requests such as '对比', 'diff', or '找不同', which can cause the skill to trigger unintentionally outside a clear user opt-in. In an agent environment, overbroad activation increases the chance of the wrong tool being invoked on unrelated user content, potentially exposing private text to processing or producing confusing behavior.

Content

No source excerpt is available for this finding.