Back to skill

Security audit

Ad Creator

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese advertising-copy methodology skill with no executable code, persistence, network behavior, or sensitive access.

Installers should know this skill may be invoked too broadly because of generic trigger words, so it is best suited for users who frequently ask for Chinese advertising or brand-copy work. It does not appear to run code or access private data.

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
  • 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 (3)

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger terms include very broad words like 'skill', '优化', '品牌', and 'brand', which are likely to appear in ordinary user conversation and unrelated tasks. This can cause accidental invocation, making the agent inject persuasive advertising methodology into contexts where the user did not intend to use this skill, increasing prompt-collision and behavioral hijacking risk.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

The skill name, description, and instructional content are entirely in Chinese, and the file does not indicate that the user can choose another language or that the skill is intentionally limited to a Chinese-language audience. Under the language/locale policy, forcing one language without opt-in can be a policy concern.

Content

No source excerpt is available for this finding.