longbridge-corporate-events
Pass
Audited by Gen Agent Trust Hub on May 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes vendor-specific CLI commands (e.g.,
longbridge news,longbridge filing) to retrieve financial data. These operations are within the scope of the skill's intended purpose and target vendor-controlled tools. - [PROMPT_INJECTION]: The skill processes external data such as news and regulatory filings, which presents a surface for indirect prompt injection. This is inherent to the functionality of financial analysis tools.
- Ingestion points: Data returned from
longbridge news,longbridge filing,longbridge corp-action, andlongbridge shareholdercommands as described in SKILL.md. - Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are defined for the fetched content.
- Capability inventory: The agent uses shell commands to interface with the Longbridge CLI for data retrieval across multiple subcommands.
- Sanitization: The instructions mandate resolving user inputs to a specific
<CODE>.<MARKET>format, which provides a level of input validation against common injection patterns.
Audit Metadata