Back to skill

Security audit

快手热点选题追踪助手

Security checks for vulnerabilities and agentic risk

Overview

ClawScan verdict: benign; scanners found no reported malicious behavior, while noting some extra data-retrieval capabilities and incomplete inspection of several files.

The verdict is benign with medium confidence, not a guarantee of safety. The scan covered 20 of 32 components fully; 12 were only partially inspected. Before installing, weigh that gap and the reported transmission of searches and links to www.guaikei.com, and avoid sending sensitive information.

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
  • 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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (26)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The declared core operation is keyword-based real-time search, but the supplied code has no keyword input or search operation. Its required input is a creator profile URL or numeric user ID, and its main calls are createPostTask and getPostTask. Although creator lookup could support the listed research use cases, it is a materially different retrieval capability from the one described. Token handling, argument validation, and output formatting are supporting implementation details, not independent mismatches.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The supplied code implements video-comment retrieval, not keyword-based real-time search. Although comments could support the broader research use cases mentioned in the description, those use cases do not accurately disclose this distinct operation. Token handling, validation, and output formatting are supporting implementation details, not separate mismatches.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The code calls /api/kuaishou/comment/url and /api/kuaishou/comment/info with a URL and limit. It contains no keyword-search operation. Although comments could support content research, retrieving them is a distinct data-access capability not disclosed by the keyword-search description. The POST request creates a retrieval task; it does not indicate posting comments.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
93% confidence
Finding

The supplied command targets a particular short video through comment-cli.js; it does not supply keywords or visibly perform a search. Although comments could support content research, retrieving them is a distinct capability not disclosed by the keyword-search description. The assessment is limited to the visible invocation because the underlying script is unavailable.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
92% confidence
Finding

Both commands target comment-cli.js and supply a video identifier rather than a keyword query. Video-comment retrieval is related to content research but is a distinct capability from the declared real-time keyword search. The CLI implementation is not included, so this conclusion is based on the invoked command and its arguments; no additional behavior is established.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
92% confidence
Finding

The supplied functions accept a URL, sort, and limit, and operate on post-specific task endpoints. They do not accept keywords or invoke a search endpoint. Although retrieving posts could support the broader research use cases, this chunk exposes a distinct URL-based retrieval capability not represented by the keyword-search description. Authentication, polling, and response validation are supporting implementation details, not additional mismatches.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
88% confidence
Finding

The supplied commands target a specific Kuaishou profile or identifier, which is a distinct retrieval mode from keyword search. Although this could support the broader research use cases mentioned in the description, profile-based collection is not disclosed as a capability. The CLI implementation is not provided, so its precise network behavior and handling of '--limit 0' cannot be established.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
87% confidence
Finding

The command targets a user profile and supplies no keyword or search query. Although profile content could support the broader research use cases, collecting posts from a specific profile is a distinct capability from the declared keyword search. The underlying script is not supplied, so its precise behavior and any additional capabilities cannot be verified.

Content

No source excerpt is available for this finding.

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 73)May include surrounding context.

md
- "帮我搜快手里「具身智能」的高赞视频 → node scripts/kuaishou/search-cli.js --keyword \"具身智能\" --sort 2 --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 74)May include surrounding context.

md
- "最近一周最新的快手 AI 教程,要 20 条 → node scripts/kuaishou/search-cli.js --keyword \"AI 教程\" --sort 1 --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 86)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 123)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 154)May include surrounding context.

md
ut 为空,这是正常现象。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/kuaishou/search-cli.js -- -AI`。完整字段见 `assets/*_cli_req.schema.json` 与 [r

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 75)May include surrounding context.

md
- "这条快手视频评论区在说什么 → node scripts/kuaishou/comment-cli.js --url \"https://www.kuaishou.com/short-video/3xabc\" --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 87)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 121)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 130)May include surrounding context.

md
- `kuaishou.com/short-video/{id}`、`v.kuaishou.com/*`、裸的 `3x...` 只能给 `comment-cli.js`。搜索结果里用视频 `id` 或 `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 146)May include surrounding context.

md
| 评论区 | `comment-cli.js`。没说条数用默认 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 76)May include surrounding context.

md
- "这个快手博主最近 20 条作品 → node scripts/kuaishou/post-cli.js --url \"https://www.kuaishou.com/profile/3xabc\" --sort 0 --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 77)May include surrounding context.

md
- "这个快手博主多少粉丝 → node scripts/kuaishou/post-cli.js --url 123456 --limit 0"

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 122)May include surrounding context.

md
2. 要作品、主页、账号、博主、粉丝 → `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 128)May include surrounding context.

md
- `kuaishou.com/profile/{id}` 只能给 `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 129)May include surrounding context.

md
- 纯数字 `user_id` 只能给 `post-cli.js`。搜索结果里用 `user.user_id`,或直接用 `user.url`

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.

The quick-start instructions omit disclosure that searches and target links are sent to a third-party service.

Medium
Category
Output Handling
Confidence
88% confidence
Finding

The README instructs users to execute searches and retrieve account or comment data, but does not explain that their keywords and links are transmitted to www.guaikei.com rather than directly to Kuaishou. Requiring a token from that website does not clearly disclose this data flow, particularly alongside the README's privacy assurances.

Content

No source excerpt is available for this finding.