feishu-notify
Fail
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: HIGHCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATION
Full Analysis
- [COMMAND_EXECUTION]: The skill documentation provides shell command templates (using
curl) that interpolate variables such as$ARGUMENTS,TITLE,BODY, andCOLORdirectly into the command line. If these variables contain shell metacharacters (e.g.,;,&,|,`, or$(...)), it could lead to arbitrary command execution when processed by the agent's shell environment. - [EXTERNAL_DOWNLOADS]: The skill explicitly references and encourages the use of an external bridge application hosted at
https://github.com/joewongjc/feishu-claude-code. This repository is not from a trusted organization or the skill author, posing a supply chain risk if the external code is malicious or compromised. - [DATA_EXFILTRATION]: The skill logic involves reading a configuration file from the user's home directory (
~/.codex/feishu.json) and transmitting data to external endpoints ($WEBHOOK_URLor$BRIDGE_URL). While this is the intended notification functionality, the combination of sensitive file access and outbound network requests provides a vector for exfiltrating environment data if the endpoints or inputs are manipulated.
Recommendations
- AI detected serious security threats
Audit Metadata