ClawHub

Feishu Voice (macOS)

v1.1.0

Send voice/audio messages to Feishu (Lark) chats using TTS. Automatically uses OpenAI TTS (gpt-4o-mini-tts) if OPENAI_API_KEY is set, otherwise falls back to...

⭐ 0· 168·0 current·0 all-time
by@zihui
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
The name/description (send voice messages to Feishu using TTS) matches the files and runtime requirements. The script needs ffmpeg/ffprobe/curl/python3 and Feishu app_id/app_secret to obtain a tenant token and upload/send audio — all expected for this feature. The SKILL.md and script both reference the same Feishu endpoints and optional OPENAI_API_KEY.
✓
Instruction Scope
Runtime instructions and the script only perform TTS (OpenAI or macOS say), transcode to opus, obtain a tenant_access_token using app_id/app_secret from ~/.openclaw/openclaw.json, upload the opus file, and send the audio message. There are no instructions to read unrelated files, escalate privileges, or exfiltrate arbitrary data beyond the Feishu/OpenAI network calls required for operation.
✓
Install Mechanism
This is instruction-only plus a small shell script — there is no installer that downloads and executes remote archives. It depends on existing local binaries (ffmpeg, ffprobe, curl, python3, and optionally macOS 'say'). That is low risk and proportionate to the task.
ℹ
Credentials
No required environment variables are declared; OPENAI_API_KEY is optional and only used to call OpenAI TTS. The skill reads sensitive Feishu credentials (app_id/app_secret) from ~/.openclaw/openclaw.json — this is necessary for the Feishu API but you should be aware the script reads those secrets directly. The number and type of credentials requested are proportional to the stated functionality.
✓
Persistence & Privilege
The skill is not always-enabled and does not request elevated or persistent system privileges. It does not modify other skills or system-wide settings; it writes temporary files to /tmp and cleans them up. Autonomous invocation is allowed (platform default) but not unusually privileged here.
Assessment
This skill appears to do exactly what it claims: generate TTS (via OpenAI or macOS), transcode to opus, and send it to Feishu using your Feishu bot credentials stored at ~/.openclaw/openclaw.json. Before installing or using it: (1) verify that your ~/.openclaw/openclaw.json contains only the expected Feishu app_id/app_secret and is stored securely, because the script will read those secrets; (2) if you enable OPENAI_API_KEY, be aware usage will call OpenAI's API (and may incur costs); (3) inspect the included scripts yourself (they are small and readable) and run a manual test to confirm behavior; (4) ensure ffmpeg/ffprobe are installed from trusted sources since they process audio; (5) if you have concerns about automatic network calls, only run the script locally or in an environment where you can monitor outbound connections. Note: the registry summary showed a minor metadata formatting oddity ('Required config paths: [object Object]') but the SKILL.md and script clearly specify the config path used.

Like a lobster shell, security has layers — review code before you run it.

latestvk976jgpeqxnv9w5vmaa1knhnhh83jpab

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Runtime requirements

Binsffmpeg, ffprobe, curl, python3
Config[object Object]

Comments