longbridge
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of additional tools and sub-skills from the official Longbridge GitHub repository (github.com/longbridge/skills).
- [COMMAND_EXECUTION]: The skill interacts with the user's environment by executing the
longbridgeCLI tool and its various subcommands to retrieve financial data. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external financial markets, including news feeds and analyst ratings, which could potentially contain malicious instructions.
- Ingestion points: External market news, analyst ratings, and sector descriptions retrieved via CLI commands in SKILL.md.
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in this guide.
- Capability inventory: The skill executes shell commands via the
longbridgeCLI and renders retrieved data to the user context. - Sanitization: No explicit sanitization or validation of the retrieved text content is described.
Audit Metadata