The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes project source code (src/**) and configuration files to generate documentation. This establishes a vulnerability surface where malicious instructions could be embedded in code comments to influence the agent's behavior during documentation generation.
Ingestion points: TypeScript source files and documentation configuration files.
Boundary markers: No specific delimiters or instructions are provided to the agent to treat content within source files as untrusted.
Capability inventory: The skill uses Read, Write, Edit, Bash, Grep, and Glob tools to perform its tasks.
Sanitization: No content filtering or sanitization is applied to the source code before processing.
[EXTERNAL_DOWNLOADS]: The documentation includes commands to install standard, well-known development tools such as typedoc, typedoc-plugin-markdown, and @compodoc/compodoc via the npm registry. These are legitimate tools for the TypeScript ecosystem.
[COMMAND_EXECUTION]: The skill utilizes shell commands via Bash for routine development operations, including installing dependencies, generating documentation with npx, and running a local documentation server using Python's built-in http.server module.

typescript-docs