Back to skill

Security audit

速转字幕

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill suspicious because scanners report a download-handling risk and an undisclosed third-party token requirement, while analysis of much of the code was incomplete.

Treat this as a review case rather than evidence that the author is malicious. Before installing, consider whether you are comfortable providing a token to the named third party and with the reported risk of losing an existing file if a resumed download fails or is stopped. The scan was partial: only 7 of 18 components were fully inspected, so the remaining behavior is not fully assessed.

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 (22)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
87% confidence
Finding

Token validation can be a legitimate supporting implementation detail, and this utility need not implement transcription itself. However, it also introduces an undisclosed third-party token dependency and advertises an external acquisition channel, neither of which is explained by the declared Qwen-powered video-processing purpose. The snippet performs no network requests, verifies no token remotely, and does not itself demonstrate that the entire skill is actually suspended.

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 55)May include surrounding context.

md
command: 'node scripts/video2text/index.js --file "https://example.com/video.mp4"'

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 57)May include surrounding context.

md
command: 'node scripts/video2text/index.js --file "/path/to/video.mp4"'

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 59)May include surrounding context.

md
command: 'node scripts/video2text/index.js --file "https://example.com/video.mp4" --prompt "总结这个视频的核心观点"'

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 61)May include surrounding context.

md
command: 'node scripts/video2text/index.js --file "/path/to/video.mp4" --prompt "改写成小红书风格的文案"'

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 63)May include surrounding context.

md
command: 'node scripts/video2text/index.js --id last --prompt "提取视频中的所有金句"'

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 65)May include surrounding context.

md
command: 'node scripts/video2text/index.js --help'

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 125)May include surrounding context.

md
| 怎么把 https://example.com/video.mp4 里的声音转成文字 | `node scripts/video2text/index.js --file "https://example.com/video.mp4"` |

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 126)May include surrounding context.

md
| 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"` |

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 127)May include surrounding context.

md
| 把本地 /path/to/video.mp4 改成小红书文案 | `node scripts/video2text/index.js --file "/path/to/video.mp4" --prompt "改写成小红书风格的文案"` |

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
| 用刚才分析的视频提取所有金句 | `node scripts/video2text/index.js --id last --prompt "提取视频中的所有金句"` |

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
| 分析这个视频的情感基调和受众 | `node scripts/video2text/index.js --file "<URL或路径>" --prompt "分析视频的情感基调和目标受众"` |

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
node scripts/video2text/index.js --file "/path/to/your/video.mp4"

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
node scripts/video2text/index.js --file "https://example.com/video.mp4"

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 160)May include surrounding context.

md
node scripts/video2text/index.js --file "/path/to/your/video.mp4" --prompt "请用三个要点总结这个视频的核心内容"

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 162)May include surrounding context.

md
node scripts/video2text/index.js --file "/path/to/your/video.mp4" --prompt "将这段内容改写成一篇风趣幽默的小红书文案"

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
node scripts/video2text/index.js --id last --prompt "提取视频中的所有金句"

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 131)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.

Stopping or failing a download can silently delete the destination file, including an existing file being resumed.

Medium
Category
Output Handling
Confidence
88% confidence
Finding

The downloader defaults to deleting its destination on stop or failure, while resumeFromFile can point that destination at a pre-existing file without recording ownership or preserving its original contents. A stopped or failed resumed transfer can therefore destroy existing data; the skill's normal unique-file download wrapper reduces exposure, but the downloader API remains unsafe for existing-file resumption.

Content

No source excerpt is available for this finding.

Startup invokes expiration-based cleanup without disclosing the deletion to the user.

Medium
Category
Output Handling
Confidence
88% confidence
Finding

The script calls clean.deleteExpire() before processing arguments, so cleanup runs even when the user only requests help. There is no confirmation, log, or explanatory comment for this deletion operation, and any cleanup error is silently suppressed.

Content

No source excerpt is available for this finding.

Incomplete downloads are deleted without disclosure.

Low
Category
Output Handling
Confidence
91% confidence
Finding

When a download is marked incomplete, the handler deletes its file with fs.unlinkSync. The error message only reports that the download is incomplete; no prompt, log, or comment explains that the partial file is removed.

Content

No source excerpt is available for this finding.