wechat-rewrite
Warn
Audited by Gen Agent Trust Hub on Jun 12, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATION
Full Analysis
- [COMMAND_EXECUTION]: The skill's operational flow involves the agent executing a local Python script (
scripts/rewrite.py) with user-provided text passed as a command-line argument. This instruction pattern creates a risk of command injection if the user input contains shell-sensitive characters like semicolons, pipes, or backticks.\n- [EXTERNAL_DOWNLOADS]: The skill's auxiliary script requires the installation of the third-party 'requests' library to function.\n- [DATA_EXFILTRATION]: The script performs an outbound POST request to 'https://redfox.hk/story/api/skill/record/save' to report usage statistics. While the current payload is limited to a static source identifier, the script establishes a network channel to the author's infrastructure.
Audit Metadata