ClawHub
Skill flagged — suspicious patterns detected

ClawHub Security flagged this skill as suspicious. Review the scan results before using.

Feishu Send Message

v2.0.2

Send private or group messages via the current Agent's Feishu app, showing the configured bot name and handling app-isolated open_id.

⭐ 0· 91·0 current·0 all-time
by@pikaqiuyaya
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Suspicious
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name/description (Feishu message sending) match the implementation: the script reads the agent-specific config (~/.openclaw/openclaw-{agent}.json) for appId/appSecret and calls open.feishu.cn to obtain a token and post messages. Required tools (curl/jq) listed in metadata are appropriate.
ℹ
Instruction Scope
Instructions and the script operate within the expected scope (read agent config, call Feishu API). The SKILL.md also instructs grepping system journal logs (journalctl) to find user open_id; this is functionally necessary to obtain open_id but means the skill will access local service logs and could surface additional log contents. The script echoes App ID, target and message to stdout (may appear in logs) — not strictly required and may leak non-secret context.
✓
Install Mechanism
No install spec; this is an instruction-only skill with a small bash script included. No external downloads or archive extraction are performed.
ℹ
Credentials
The skill does not request environment variables but reads local config files that contain the Feishu app_id and app_secret. Access to those files is proportionate for sending messages, but those files contain sensitive credentials (app_secret). The metadata expects jq/curl; ensure those are trusted binaries on PATH.
✓
Persistence & Privilege
always is false and the skill does not persist new credentials or modify other skills. It runs on-demand and does not request elevated system privileges.
Assessment
This skill appears to do what it says: it reads the agent's local Feishu config (~/.openclaw/openclaw-{agent}.json) to obtain app_id and app_secret and posts to the official Feishu API. Before installing, verify you trust the skill source (homepage/source unknown), confirm the config files contain only expected credentials, and be aware the SKILL prints the App ID, target and message (which may end up in shell or agent logs). If you do not want the skill to read system logs to extract open_id, manually obtain open_id and call the script. Reject the skill if you see network targets other than open.feishu.cn or any obfuscated/remote-downloaded code in future versions.

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

latestvk9770wvy1adz37vmvx9626yv4d8388dt

License

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

Comments