Back to skill

Security audit

Tk Product Launch Os

Security checks for vulnerabilities and agentic risk

Overview

This is a TikTok ecommerce planning playbook with some broad routing language, but it does not include hidden execution, credential use, or unsafe system behavior.

Install this if you want a Chinese-language operating guide for TikTok product launches. Keep sensitive commercial information such as costs, supplier details, account names, video IDs, and sales records under your control, and be aware that broad TikTok/TK wording may make the skill activate for adjacent discussions.

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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The activation conditions describe positive cases but do not define boundaries, exclusions, or negative examples, so the skill may trigger on partially related conversations. In an agent system, ambiguous routing is a real security and safety concern because it can cause the wrong skill to take control, produce off-target outputs, or interfere with more appropriate workflows.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger keywords are very broad, including generic terms like 'TK', 'TikTok', '选品', and '爆款视频', which can overlap with routine discussion and unrelated content analysis requests. This can cause the skill to activate outside its intended scope, leading to irrelevant guidance, reduced agent reliability, or accidental handling of conversations that should be routed elsewhere.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
77% confidence
Finding

L004 的描述全文为中文,整体文档也默认以中文进行说明和交互,但没有向用户提供语言或地区偏好的选择。按照语言/locale 政策,若技能默认强制特定语言而无用户选择,属于自然语言层面的潜在政策问题。

Content

No source excerpt is available for this finding.