china-morning-note
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface due to its core function of ingesting and summarizing real-time financial news from third-party platforms.
- Ingestion points: The skill retrieves market headlines and news from tools such as
ifind_search_news,get_stock_news, and thechina-newsMCP service. - Boundary markers: The workflow does not define specific delimiters or instructional guards to prevent the agent from executing commands that might be embedded within the retrieved news text.
- Capability inventory: The agent uses collected data to formulate trade ideas, investment logic, and market strategy notes.
- Sanitization: No mechanisms for filtering or validating the safety of the external content are specified before the information is processed by the agent.
Audit Metadata