daily-stock-analysis

Pass

Audited by Gen Agent Trust Hub on Mar 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill fetches and summarizes external data, which is an inherent vulnerability surface.
  • Ingestion points: Market news, technical indicators, and fundamental data are retrieved from various external APIs including Tavily, SerpAPI, Brave, AkShare, and YFinance.
  • Boundary markers: The documentation does not specify the use of delimiters or instructions to the LLM to ignore embedded commands within the processed news text.
  • Capability inventory: The skill has the capability to perform network requests and push data to multiple notification platforms (Telegram, Discord, WeChat, etc.) based on AI analysis results.
  • Sanitization: There is no mention of input sanitization or filtering for the external news content before it is processed by the LiteLLM backend.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 17, 2026, 07:54 PM