typescript-docs
Pass
Audited by Gen Agent Trust Hub on Feb 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of well-known development tools such as typedoc and typedoc-plugin-markdown from the official npm registry.
- [COMMAND_EXECUTION]: The skill provides standard terminal commands for documentation tasks, including building API references with npx and serving local files using Python's built-in HTTP server module.
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because it is designed to ingest and document external TypeScript source code.
- Ingestion points: Source code is read using the Read and Glob tools.
- Boundary markers: No explicit delimiters or instructions are used to separate source code content from agent instructions.
- Capability inventory: The agent has access to Write, Edit, and Bash tools, which could be exploited if malicious instructions in code comments are followed.
- Sanitization: The skill does not implement specific sanitization or filtering for the content of JSDoc comments before documentation generation.
Audit Metadata