typescript-lsp
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to run
npx typescript-language-server --stdioto start the language server, which is the standard method for using this tool in a development environment. - [INDIRECT_PROMPT_INJECTION]: 1. Ingestion points: The skill transmits code file content to the language server through the
textDocument/didOpenmethod (SKILL.md). 2. Boundary markers: The instructions do not define specific delimiters or boundary markers for the data being processed. 3. Capability inventory: The agent is authorized to perform local file reads and command execution within the repository context. 4. Sanitization: No specific sanitization or filtering of the source code content is performed before processing. However, this surface is inherent to the primary function of a language server and does not pose an elevated risk in this context.
Audit Metadata