wecom-notify

Pass

Audited by Gen Agent Trust Hub on Mar 2, 2026

Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The script scripts/send_wecom.py accesses sensitive configuration at ~/.openclaw/openclaw.json to retrieve the WECOM_CORP_SECRET and other credentials.
  • [DATA_EXFILTRATION]: The skill is designed to read local files using the read_bytes() method in scripts/send_wecom.py and upload them to the well-known WeCom API service at qyapi.weixin.qq.com.
  • [PROMPT_INJECTION]: Vulnerability to indirect prompt injection (Category 8).
  • Ingestion points: Command-line arguments (message, --image, --file) in scripts/send_wecom.py which may contain untrusted data from the agent context.
  • Boundary markers: No markers or delimiters are used when interpolating input into the JSON payload for the WeCom API.
  • Capability inventory: File system read access and network transmission capabilities via urllib.request.
  • Sanitization: The skill does not sanitize or validate the message content or file paths before processing and sending them externally.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 2, 2026, 05:48 AM