feishu-voice-sender

Fail

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: HIGHCREDENTIALS_UNSAFECOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
  • [CREDENTIALS_UNSAFE]: The skill accesses sensitive credentials by reading from the local file system at ~/.openclaw/.env. It specifically looks for FEISHU_APP_ID and FEISHU_APP_SECRET to authenticate with the Feishu API. There is also a discrepancy as the documentation suggests a different path (~/.openclaw/config/main.env), which could lead to confusion regarding where secrets are stored.
  • [COMMAND_EXECUTION]: The script executes the system command ffmpeg via subprocess.run to handle audio conversion. While it passes arguments as a list, it processes user-supplied file paths directly as inputs to this command.
  • [DATA_EXFILTRATION]: There is a significant risk of data exfiltration due to a fallback mechanism in the convert_to_amr function. If the ffmpeg conversion fails (e.g., when a text file or private key is provided instead of audio), the code uses shutil.copy to move the original file to a temporary location and then uploads it to the Feishu servers (https://open.feishu.cn/open-apis/im/v1/files). This behavior allows the agent to be manipulated into uploading arbitrary local files to a remote API.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Mar 3, 2026, 02:38 PM