wechat-original-hot

Pass

Audited by Gen Agent Trust Hub on Aug 18, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXPOSURE_AND_EXFILTRATION]: The skill uses an environment variable DOUBAOYA_API_KEY for authentication. The instructions explicitly state that the key should not be printed, written to files, or echoed to users, which aligns with security best practices.
  • [EXTERNAL_DOWNLOADS]: The skill communicates with a single external domain, doubaoya.com, which is the intended provider for the data requested by the skill. The Python script uses the standard urllib library to make POST requests to the API endpoint.
  • [COMMAND_EXECUTION]: The skill documentation suggests using shell commands to calculate date offsets (e.g., date -d '-9 days'). These are standard utility commands used to format arguments for the Python script and do not present a security risk in this context.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from the WeChat Official Accounts API. While it presents this data to the user in a table and provides a 'creative insight', the ingestion point (the API response) is handled by a script that outputs JSON to the AI. The AI then renders this into a table. Standard boundaries apply.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 18, 2026, 11:42 AM
Security Audit — agent-trust-hub — wechat-original-hot