audio-transcribe@1.0.0

CAUTION

Publisher claims: "输入一段音频录音文件——本地音频文件（MP3/WAV/M4A/AAC/FLAC/OGG）或在线音频链接——输出**带时间戳、可区分说话人**的文字稿，并附一份总结分析。底层经 Cue Omni Reader 解析（ASR 语音识别 + 说话人分离），再由大模型分段整理交付。适用于会议录音、访谈、讲座、通话录音、口述笔记等。" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher panting09266-ai · joined 1 days agoInstalls 0Last detonated 23 h ago

Dispute verdict

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations

t+CategoryObserved action

0.0sprocessno install scripts in bundle

0.0sprocessscript backend runs setup only

Static findings

HIGH

Python subprocess execution detectedSKILL.md:254 · Python subprocess execution detected

AST05

HIGH

npx invocation of non-well-known packageSKILL.md:239 · npx invocation of non-well-known package — may execute untrusted code

AST06

HIGH

npx invocation of non-well-known packageSKILL.md:54 · npx invocation of non-well-known package — may execute untrusted code

AST06

HIGH

npx invocation of non-well-known packageSKILL.md:88 · npx invocation of non-well-known package — may execute untrusted code

AST06

HIGH

npx invocation of non-well-known packageSKILL.md:338 · npx invocation of non-well-known package — may execute untrusted code

AST06

HIGH

npx invocation of non-well-known packageSKILL.md:81 · npx invocation of non-well-known package — may execute untrusted code

AST06