longbridge-event-strategy

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes data from external corporate news and filings which could contain adversarial instructions.
  • Ingestion points: Market news and corporate filings are retrieved via longbridge news and longbridge filing (SKILL.md).
  • Boundary markers: There are no explicit instructions or delimiters used to separate user/system instructions from the external text being analyzed.
  • Capability inventory: The skill utilizes the longbridge CLI for data retrieval. Its actions are primarily focused on data analysis and reporting.
  • Sanitization: No sanitization or validation of the external text is performed before it is processed by the agent.
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute vendor-specific CLI commands (longbridge news, longbridge filing, longbridge finance-calendar, longbridge kline). These tools are used for their intended purpose of retrieving financial data for investment analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 11:55 AM