longbridge-morning-brief

Pass

Audited by Gen Agent Trust Hub on May 11, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the longbridge command-line interface (CLI) to retrieve financial data, including quotes, earnings calendars, news, and capital flow information. These commands (longbridge quote, longbridge news, etc.) are part of the vendor's own ecosystem and are used for their intended analytical purposes.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data such as news headlines and calendar events which could theoretically contain malicious instructions.
  • Ingestion points: External data is ingested via longbridge news <SYMBOL> and longbridge finance-calendar as described in SKILL.md.
  • Boundary markers: The instructions do not specify the use of delimiters (e.g., XML tags or triple quotes) when the agent processes the fetched news content.
  • Capability inventory: The skill's capabilities are limited to executing the specific longbridge CLI subcommands for data retrieval; it does not contain scripts for file-writing, arbitrary shell execution, or persistent network operations.
  • Sanitization: There is no explicit instruction for the agent to sanitize or filter the content of the news articles before summarization.
Audit Metadata
Risk Level
SAFE
Analyzed
May 11, 2026, 04:42 AM