Back to skill

Security audit

抖音评论分析 GuaiKei 评论洞察

Security checks for vulnerabilities and agentic risk

Overview

The skill retrieves public Douyin data through a disclosed third-party service and saves results locally as documented.

Use it if you accept sending your queries and links to www.guaikei.com under that provider's terms and pricing. Keep the API token private, choose suitable retrieval limits, and protect or delete saved logs containing inputs and public user data.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Findings (14)

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
- '这个博主最近 30 条作品 → node src/douyin/post-cli.js --url "https://www.douyin.com/user/MS4wLjABxxx" --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 116)May include surrounding context.

md
- '看看这个对标账号多少粉丝、多少获赞 → node src/douyin/post-cli.js --url "https://www.douyin.com/user/MS4wLjABxxx" --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 138)May include surrounding context.

md
| 品牌 / 投放 | 监控对标账号的发文节奏与内容策略 | `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 153)May include surrounding context.

md
| 博主作品、主页、对标账号、粉丝数据 | `node src/douyin/post-cli.js` | 主页链接或 `sec_uid` |

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 174)May include surrounding context.

md
### 4.2 博主作品 `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 117)May include surrounding context.

md
- '这条视频的评论区都在说什么 → node src/douyin/comment-cli.js --url "https://www.douyin.com/video/xxx" --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 139)May include surrounding context.

md
| 舆情 / 客服 | 判断一条视频的评论区在骂还是在夸 | `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 154)May include surrounding context.

md
| 某条视频/图文的评论 | `node src/douyin/comment-cli.js` | 视频链接或 `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 183)May include surrounding context.

md
### 4.3 视频评论 `comment-cli.js`

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · references/changelog.md (reported line 85)May include surrounding context.

md
- 技能重命名为“douyin-search-keyword”。
- 在SKILL.md中添加了openclaw元数据、使用帮助、许可证、标签和示例,以实现更好的集成与文档化。
- 移除了两个本地文件(.env 和 scripts/last-search.json),以优化代码结构并提升安全性。
- 文档现已更加简洁且以用户为中心,重点在于提供清晰的使用说明和数据字段解释。
- 突出技能特性、合规要点及技术流程。

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.

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 · SKILL.md (reported line 185)May include surrounding context.

md
### 4.3 视频评论 `comment-cli.js`

| 参数      | 缩写 | 必填 | 取值                                                                                   | 默认 |
| --------- | ---- | ---- | -------------------------------------------------------------------------------------- | ---- |
| `--url`   | `-u` | ✅   | `douyin.com/video/xxx`、`douyin.com/note/xxx`、`v.douyin.com/xxx`,或纯数字 `aweme_id` | —    |
| `--limit` | `-l` |      | 1–10000                                                                                | 10   |

Comment results are saved to a local JSON log without disclosing persistence to the user.

Medium
Category
Output Handling
Confidence
92% confidence
Finding

The CLI writes the full result envelope, including retrieved comments and the original input URL, through log.writeResultLog. Its help text, comments, and user-facing messages describe retrieving comments but do not disclose saving this data locally; persistence is not inherent to the stated retrieval purpose.

Content

No source excerpt is available for this finding.

Retrieved data is automatically persisted to a JSON log without disclosing the file write.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

The command writes the complete result envelope, including the requested URL and returned profile/post data, to a JSON log. The provided file describes and reports retrieval but contains no confirmation, user-facing notice, or explanatory comment disclosing this additional persistence.

Content

No source excerpt is available for this finding.