wechat-hot-write
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Python script (
hot_write.py) to fetch data from the backend API. This is a standard operation to retrieve sample content for the agent to analyze.\n- [PROMPT_INJECTION]: The skill processes untrusted external data (article titles and metadata) fetched from an API, creating a potential surface for indirect prompt injection.\n - Ingestion points: The
hot_write.pyscript retrieves external content fromdoubaoya.comand outputs it to the agent.\n - Boundary markers: The instructions do not define explicit delimiters or instructions to ignore potential injection attempts within the fetched data.\n
- Capability inventory: The agent uses the data for analysis and text generation; no high-risk capabilities like system modification or sensitive file access are involved.\n
- Sanitization: There is no evidence of explicit content sanitization or filtering for the retrieved article data before it is processed by the agent.
Audit Metadata