Back to skill

Security audit

GUAIKEI快手内容研究助手

Security checks for vulnerabilities and agentic risk

Overview

ClawScan labels this skill benign with medium confidence: it found no AIG issues and judged its Kuaishou research functions broadly aligned, while noting incomplete inspection and some disclosure and description concerns.

The verdict is benign, but the scan was partial: only 20 of 32 components were fully scanned, and 12 were partially inspected. Before installing, consider that Skillspector reported unclear disclosure of query-input transmission to a third party and a mismatch between the stated keyword-search purpose and some retrieval functions. Avoid sending sensitive keywords, links, or IDs unless you are comfortable with that transmission.

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 (27)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied code implements creator-specific content retrieval, not the declared keyword-based real-time search capability. Although creator data can support the listed research use cases, the primary operation and required input materially differ from the description. Authentication, argument validation, and JSON logging 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's primary operation is video-comment retrieval, not real-time keyword search. Although comments could support the broadly listed research use cases, that does not accurately describe this distinct capability. Token handling, validation, output formatting, and result logging are supporting implementation details and are not independently flagged.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The supplied command targets an individual video through --url and invokes a comment-specific CLI; it provides no keyword-search input. Although comment collection could support content research, it is a distinct data-retrieval capability from the declared keyword search. The CLI implementation is not supplied, so its exact behavior cannot be independently verified.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

The code calls /api/kuaishou/comment/url and /api/kuaishou/comment/info using a URL and limit. This implements comment collection, a distinct capability not disclosed by the keyword-search description. Although comments could support the listed research activities, those broad use cases do not establish that comment retrieval is part of the declared functionality. No keyword-search behavior appears in the supplied chunk.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
94% confidence
Finding

The supplied code operates on a URL and post-specific task endpoints, with no keyword input or keyword-search operation. Although retrieving posts could support the broader research use cases, its implemented retrieval mode materially differs from the explicitly declared keyword-search capability. Task polling, authentication, and result validation 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
90% confidence
Finding

Video-specific comment retrieval is a distinct capability not disclosed by the keyword-search description. Although comments could support content research, these commands do not perform the declared search operation. The CLI implementation is not supplied, so this assessment is limited to the behavior indicated by the commands.

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 through post-cli.js, whereas the description specifically advertises keyword-based real-time search. Although profile-post retrieval could support the listed research activities, it is a distinct retrieval capability not disclosed in the description. The CLI implementation is not supplied, so its exact behavior and any additional effects cannot be verified.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
86% confidence
Finding

The supplied command targets a user profile and supplies no keyword-search input. Although profile content could support the broader research use cases, it differs from the specific retrieval capability declared. The script implementation is not supplied, so its exact retrieval behavior and any additional side effects 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 usage instructions omit disclosure that user-supplied keywords and links are transmitted to a third-party service.

Medium
Category
Output Handling
Confidence
88% confidence
Finding

The quick-start instructions identify a token provider but do not explicitly explain that search keywords and target links are sent to that third party. Public source content does not make the user's research interests public, so confidential campaign terms or investigation targets could be disclosed without an informed decision.

Content

No source excerpt is available for this finding.