Security audit

TikTok达人发现与洞察

Security checks for vulnerabilities and agentic risk

Overview

ClawScan classifies this TikTok discovery skill as benign with medium confidence; the main caveat is that several scripts were only partially inspected, so the evidence is incomplete.

The verdict is benign, but treat it as a limited assessment rather than a guarantee: only 20 of 32 components were fully inspected, and the tool-misuse analyzer was degraded. Consider whether you are comfortable installing with that uncertainty, and review the skill's declared scope and fixed timestamp setting.

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

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands

Findings (19)

Incomplete referenced artifact analysis

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 115)May include surrounding context.
md
- "帮我搜 TikTok 上 AI 点赞最多的视频 → node scripts/tiktok/search-cli.js --keyword \"AI\" --sort 1 --limit 20"

Incomplete referenced artifact analysis

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 116)May include surrounding context.
md
- "最近一周 TikTok 的 AI model，要 20 条 → node scripts/tiktok/search-cli.js --keyword \"AI model\" --time 7 --limit 20"

Incomplete referenced artifact analysis

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 129)May include surrounding context.
md
| 找选题、看高赞 | `search-cli.js` | 视频数组。点赞、播放、评论是数字 |

Incomplete referenced artifact analysis

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 165)May include surrounding context.
md
3. 有关键词，且没有上面两类信号 → `search-cli.js`

Incomplete referenced artifact analysis

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 195)May include surrounding context.
md
0，stdout 为空。短参数大小写都可以。含空格的关键词用双引号包成一个参数。关键词以 `-` 开头时写成 `--keyword=-AI`，或 `node scripts/tiktok/search-cli.js -- -AI`。完整字段见 `assets/*_cli_req.schema.json` 与 [ref

Incomplete referenced artifact analysis

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 117)May include surrounding context.
md
- "这个 TikTok 博主最近 30 条作品 → node scripts/tiktok/post-cli.js --url \"https://www.tiktok.com/@username\" --sort 0 --limit 30"

Incomplete referenced artifact analysis

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 118)May include surrounding context.
md
- "这个 TikTok 博主什么最火 → node scripts/tiktok/post-cli.js --url \"https://www.tiktok.com/@username\" --sort 1 --limit 30"

Incomplete referenced artifact analysis

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 120)May include surrounding context.
md
- "盯一下这个竞品账号最近发了什么 → node scripts/tiktok/post-cli.js --url \"https://www.tiktok.com/@competitor\" --limit 10"

Incomplete referenced artifact analysis

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 131)May include surrounding context.
md
| 看博主作品 | `post-cli.js` | 作品数组。没有单独的粉丝总数对象 |

Incomplete referenced artifact analysis

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 164)May include surrounding context.
md
2. 要作品、主页、账号、博主、达人 → `post-cli.js`

Incomplete referenced artifact analysis

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 170)May include surrounding context.
md
- `tiktok.com/@用户名` 只能给 `post-cli.js`。`http`、缺 `www`、`m.tiktok.com` 会在本地改成 `https://www.tiktok.com/@用户名`

Incomplete referenced artifact analysis

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 171)May include surrounding context.
md
- 整段 `MS4w` 开头的 `sec_uid` 只能给 `post-cli.js`。搜索结果用 `author_sec_uid`，或 `author_url`

Incomplete referenced artifact analysis

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 119)May include surrounding context.
md
- "这条 TikTok 视频评论区在说什么，帮我归纳舆情 → node scripts/tiktok/comment-cli.js --url \"https://www.tiktok.com/@username/video/1234567890123456789\" --limit 40"

Incomplete referenced artifact analysis

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 130)May include surrounding context.
md
| 看评论区 | `comment-cli.js` | 评论数组 |

Incomplete referenced artifact analysis

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 163)May include surrounding context.
md
1. 要评论、留言、舆情，且对象是一条视频 → `comment-cli.js`

Incomplete referenced artifact analysis

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 172)May include surrounding context.
md
- `tiktok.com/@用户名/video/数字` 和纯数字 `aweme_id` 只能给 `comment-cli.js`。搜索或作品结果用 `aweme_id`

Incomplete referenced artifact analysis

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 187)May include surrounding context.
md
| 评论区 | `comment-cli.js`。没说条数用默认 10 |

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: env.

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.

Timestamp formatting is fixed to Beijing time without user opt-in or a documented regional justification.

Low

Category: Output Handling
Confidence: 85% confidence
Finding: The comments explicitly specify fixed Beijing time for timestamps, and both formatting functions enforce that regional setting. The file provides neither a user-selectable timezone nor a justification for requiring this locale constraint.
Content: No source excerpt is available for this finding.