trading-agents

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The analyst components (news, market, fundamentals, and social analysts) fetch data from the Alpha Vantage API using curl. Alpha Vantage is a well-known service for financial market data. The skill also references an external GitHub repository (TauricResearch/TradingAgents) which serves as the conceptual basis for the workflow.
  • [COMMAND_EXECUTION]: The analyst markdown files instruct the agent to use curl commands to retrieve financial data in CSV and JSON formats from external API endpoints.
  • [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it ingests untrusted data from the web.
  • Ingestion points: The news-analyst.md and social-analyst.md files fetch and process NEWS_SENTIMENT data, which contains external headlines and summaries from various news and social media sources.
  • Boundary markers: The instructions do not define specific delimiters or warnings to ignore embedded instructions within the fetched news data.
  • Capability inventory: The skill writes multiple markdown reports to the local file system (report/ directory) and performs network requests via curl to fetch data.
  • Sanitization: The skill does not mention specific sanitization or filtering of the retrieved external content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 12:41 AM