md2wechat
Fail
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
- EXTERNAL_DOWNLOADS (HIGH): The file
scripts/run.shis designed to download binary executables fromhttps://github.com/hansonyyds/md2wechat-skill/releases. This source is not part of the 'Trusted External Sources' list. - REMOTE_CODE_EXECUTION (HIGH): After downloading the binary, the script uses
chmod +xto make it executable and then usesexecto run it with arbitrary arguments. Since the binary is hosted on an untrusted repository, its behavior cannot be audited or verified, representing a high-risk remote code execution vector. - COMMAND_EXECUTION (MEDIUM): The script acts as a wrapper that passes user-provided arguments directly to an opaque binary. If used by an agent, this could lead to unintended command execution depending on the binary's internal logic.
- DATA_EXPOSURE & EXFILTRATION (LOW): While no hardcoded secrets were found, the documentation in
references/image-syntax.mdindicates the use of sensitive environment variables likeIMAGE_API_KEY. The binary has the potential to access these variables and exfiltrate them via network calls (which it already performs for image generation and WeChat uploads).
Recommendations
- AI detected serious security threats
Audit Metadata