Back to skill

Security audit

guaikei视频大纲提取

Security checks for vulnerabilities and agentic risk

Overview

This skill needs review because its video-upload destinations are broader than its documentation promises.

Before sending confidential recordings, ask the publisher to identify and restrict storage destinations and clarify retention guarantees. Cloud upload and paid-token use are disclosed, but the single-domain privacy assurance is inaccurate. Downloaded copies can also remain locally until a later cleanup run. These concerns warrant review; the artifacts do not establish malicious intent.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (5)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
90% confidence
Finding

令牌格式校验本身可以属于正常实现细节,但该代码还将技能可用性与未声明的第三方私有令牌绑定,并在校验失败时宣传获取渠道和“解锁全部功能”,超出了声明中的视频转写与文案处理用途。此代码片段没有实际访问推广网站、发送令牌或执行视频处理;不能据此认定存在数据外传,也不能仅因辅助模块不包含转写逻辑而判定不符。

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 · README.md (reported line 99)May include surrounding context.

md
4. 同时传入文件路径与任务ID,优先执行 `--id`,忽略 `--file`
5. 无自定义 prompt 时,默认完整转录视频全部文字

| 用户自然语言指令                                         | 自动生成命令                                                                                                |
| -------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------- |
| 视频提取 https://example.com/video.mp4 中的文字          | `node scripts/video2text/index.js --file "https://example.com/video.mp4"`                                   |
| 把本地 /path/to/your/video.mp4 改成小红书风格的文案      | `node scripts/video2text/index.js --file "/path/to/your/video.mp4" --prompt "改写成小红书风格的文案"`       |

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 132)May include surrounding context.

md
当用户用自然语言下达指令时,按以下映射生成命令,保证识别与执行一致:

| 用户自然语言指令                                     | 生成的命令                                                                                                  |
| ---------------------------------------------------- | ----------------------------------------------------------------------------------------------------------- |
| 提取 https://example.com/video.mp4 里的文字          | `node scripts/video2text/index.js --file "https://example.com/video.mp4"`                                   |
| 总结这个视频的核心观点 https://example.com/video.mp4 | `node scripts/video2text/index.js --file "https://example.com/video.mp4" --prompt "总结这个视频的核心观点"` |

Stopping or failing a download silently deletes the destination file by default.

Medium
Category
Output Handling
Confidence
91% confidence
Finding

Deleting a newly created partial download is normal cleanup, but this implementation does not distinguish newly created files from pre-existing files opened through resumeFromFile(), resumeIfFileExists, or overwrite options. Because removeOnStop and removeOnFail default to true, cancellation or a download failure can delete a pre-existing destination file; an attacker-controlled server could induce such a failure when these modes are used. This creates a conditional local data-loss risk in the video-download workflow, rather than evidence of malicious behavior or arbitrary file deletion under the default unique-filename flow.

Content

No source excerpt is available for this finding.