TikTok新闻简报

• Outcome: Review
• Latest audit: Oct 19, 2026 · 9:14 AM UTC
• Version: 1.0.0

Overview

This skill appears to do what it says: retrieve public TikTok data through GUAIKEI using an API token and save JSON results locally for later analysis.

Before installing, confirm you are comfortable sending your GUAIKEI API token and TikTok queries, profile URLs, video IDs, or comment targets to www.guaikei.com. Treat saved result logs as potentially sensitive because they can include usernames, comment text, and research keywords; delete or protect the temp log files when they are no longer needed.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration

Findings (32)

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 99% confidence

Finding

The declared description promises a TikTok-focused data retrieval and analysis skill. However, the supplied code contains no TikTok-specific logic, no network access, no scraping/API interaction, no search, no comment retrieval, no aggregation, and no summarization or analysis. It is only a reusable utility for parsing command-line arguments. While such a utility could support a larger TikTok tool, this code chunk by itself does not implement the declared functionality, so the description does not accurately represent the actual behavior of the provided code.

Content

No source excerpt is available for this finding.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 98% confidence

Finding

The declared description promises substantive TikTok data collection and analysis capabilities. However, the provided code chunk is only a utility module for printing a banner and colored log messages to stderr. While such logging can be a supporting component within a larger TikTok analysis tool, this chunk by itself does not implement any of the declared end-user capabilities. Therefore, the behavior shown in the supplied code does not accurately represent the declared functionality, making this a mismatch.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium

• Category: MCP Least Privilege
• Confidence: 70% confidence

Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

• Category: Not specified by scanner
• Confidence: 94% confidence

Finding

The description forces a specific language for users and agents consuming the skill metadata, but the file does not offer an opt-in language choice or explain that the skill is intentionally limited to Chinese-language users. This matches the policy category for language or locale constraints without user choice.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 95% confidence

Finding

This JSON manifest/config file contains user-facing natural language that forces a specific language locale. The file does not offer any language choice or document a justified region-specific constraint, which matches the policy-violation criteria for language/locale restrictions.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 92% confidence

Finding

The package description advertises the skill for a very broad set of generic analysis and intelligence-gathering scenarios, which can cause over-activation outside its narrowly intended TikTok use case. In agent ecosystems, this increases the chance the skill is selected for unrelated tasks and then processes sensitive or inappropriate inputs, expanding misuse and data-exposure risk.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

• Category: Not specified by scanner
• Confidence: 95% confidence

Finding

The description is written only in Chinese and implies Chinese-language behavior without stating user choice or locale constraints. In multi-language agent environments, this can cause unexpected language coercion, misinterpretation of outputs, or bypass of user expectations and downstream controls that assume the user's selected language.

Content

No source excerpt is available for this finding.

Whitespace Padding

Medium

• Category: Prompt Injection
• Confidence: 70% confidence

Finding

Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.

Content

Scanner excerpt · references/options.md (reported line 14)May include surrounding context.

node scripts/tiktok/search-cli.js --keyword <关键词> [--sort <排序>] [--time <时间>] [--limit <数量>]

text

| 参数        | 缩写 | 作用       | 可选值                                                                                      | 必填 | 默认 |
| ----------- | :--: | ---------- | ------------------------------------------------------------------------------------------- | :--: | :--: |
| `--keyword` | `-k` | 搜索关键词 | 2–100 字符；不可含 `< > " ' &`，不可含 http 链接                                            |  是  |  —   |
| `--sort`    | `-s` | 排序方式   | `0` 相关度 / `1` 最多点赞                                                                   |  否  | `0`  |

Missing User Warnings

Medium

• Category: Not specified by scanner
• Confidence: 92% confidence

Finding

The skill documents bulk retrieval of TikTok author and public content metadata without any privacy, lawful-use, retention, or data-minimization warning. In an agent setting, this can normalize collection of profile-linked data at scale and lead to downstream misuse, especially when combined with aggregation and analysis workflows.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium

• Category: Not specified by scanner
• Confidence: 94% confidence

Finding

The comment retrieval section exposes commenter identifiers, text, and interaction metrics but provides no warning about privacy sensitivity or handling requirements. Because comment text may contain personal data or sensitive opinions, omission of safeguards increases the risk of surveillance, profiling, or improper redistribution when used by autonomous agents.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium

• Category: Not specified by scanner
• Confidence: 92% confidence

Finding

The CLI persists fetched TikTok comment data to a local JSON file after printing the structured output. Comment content, author identifiers, and interaction metadata can contain sensitive or regulated data, and silently writing them to disk creates an unnecessary secondary data store that may be accessed by other local users, collected by backup/sync tools, or retained longer than intended. In this skill context, the risk is elevated because large-scale social media intelligence workflows often process third-party data and may run in shared agent or automation environments.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium

• Category: Not specified by scanner
• Confidence: 91% confidence

Finding

The CLI persists fetched TikTok results to a local JSON file automatically after successful execution, and those results can include comment content, usernames, interaction data, links, and other potentially sensitive or regulated data. Because this happens without an explicit user-facing disclosure, opt-in, retention control, or obvious destination control in this file, it increases the risk of unintended local data exposure, especially on shared hosts, CI runners, or multi-user environments.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium

• Category: Not specified by scanner
• Confidence: 93% confidence

Finding

The CLI persists full search output to a local JSON file whose name includes the user-supplied keyword, without any opt-in, warning, or sanitization shown here. In this skill’s context, searches may involve sensitive monitoring topics, people, or investigations, so automatic local retention can leak operationally sensitive queries and collected TikTok data to other local users, backups, or downstream tooling.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

• Category: Not specified by scanner
• Confidence: 95% confidence

Finding

This JavaScript file contains user-facing natural-language messages exclusively in Chinese, including errors, warnings, and help output. The policy requires avoiding forced language or locale constraints unless the skill offers user choice or clearly documents a justified region-specific limitation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

• Category: Not specified by scanner
• Confidence: 93% confidence

Finding

Multiple user-visible error strings such as "请求失败", "响应解析失败", and "网络错误" are emitted only in Chinese. This enforces a specific language in the skill behavior with no evidence of user opt-in or a documented region-specific justification, which matches the language/locale policy violation criteria.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

• Category: Not specified by scanner
• Confidence: 97% confidence

Finding

This code emits user-facing warning and info messages only in Chinese ("警告..." and "已使用配置的私有TOKEN"). The policy requires flagging language or locale constraints when a skill forces a specific language without user opt-in, and no alternative language option or justification is provided here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

• Category: Not specified by scanner
• Confidence: 89% confidence

Finding

This JavaScript file contains natural-language comments and error messages exclusively in Chinese, including user-facing output at L26 and L32. Under the policy, forcing a specific language without user opt-in or documented regional justification is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low

• Category: Not specified by scanner
• Confidence: 97% confidence

Finding

The output contract example identifies the skill as tiktok-creator-videos instead of the declared skill name. While not directly enabling code execution, identity inconsistency can mislead agents, reviewers, or downstream automation into attributing output to the wrong skill, weakening trust boundaries and potentially causing improper routing or policy decisions.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

• Category: Not specified by scanner
• Confidence: 89% confidence

Finding

This JSON schema contains natural-language title and description fields exclusively in Chinese, which can impose a specific language on users or downstream tooling without any opt-in or documented locale limitation. Under the policy, forcing a specific language without user choice is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

• Category: Not specified by scanner
• Confidence: 95% confidence

Finding

The schema's title and property descriptions are written entirely in Chinese, which imposes a specific language on users without offering a language choice or documenting a justified region-specific constraint. Under the policy, language-only natural-language content can be a locale-policy violation when no opt-in or justification is present.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

• Category: Not specified by scanner
• Confidence: 85% confidence

Finding

This JSON schema contains human-facing title and description text entirely in Chinese, including the top-level title/description and many property descriptions. Because the file does not indicate that the skill is region-specific or provide any user opt-in for language/locale, it appears to impose a specific language by default, which matches the natural-language locale policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

• Category: Not specified by scanner
• Confidence: 92% confidence

Finding

This JSON schema uses Chinese-only natural-language titles and descriptions such as the title and parameter descriptions, with no indication that the skill is region-specific or that users can choose another language. Under the policy, forcing a specific language without opt-in or justification is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

• Category: Not specified by scanner
• Confidence: 96% confidence

Finding

This JSON schema contains user-facing natural-language metadata in Chinese only, such as the title and description. The policy requires avoiding forced language or locale constraints unless the skill offers a choice or clearly documents a justified region-specific limitation, which is not present here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

• Category: Not specified by scanner
• Confidence: 89% confidence

Finding

This file presents all workflow instructions and guardrails only in Chinese, which can amount to a language/locale policy issue when no user opt-in or alternative language is offered. The content does not indicate that the skill is intentionally region-specific or that users can choose their preferred language.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low

• Category: Not specified by scanner
• Confidence: 95% confidence

Finding

文件前文一直在描述 TikTok 新闻简报技能，但统一输出示例的 metadata 中将 skill_name 写成了 tiktok-creator-videos。这会让调用方误解该文档对应的是另一个技能，属于文档对技能意图/身份的主动性错误陈述。

Content

No source excerpt is available for this finding.

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical

• Code: suspicious.exposed_secret_literal
• Location: SKILL.md:16