The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted external content, such as JavaScript source files and package metadata, and possesses capabilities that could be influenced by malicious instructions embedded within that data. 1. Ingestion points: Processes .js, .mjs, .cjs files, and package.json during the analysis, implementation, and validation phases. 2. Boundary markers: The skill lacks explicit instructions to the agent to ignore or delimit instructions found within the processed code or configuration files. 3. Capability inventory: The skill is instructed to perform file system operations and execute shell commands (eslint --fix and jest). 4. Sanitization: No specific input validation or sanitization routines are defined.
[EXTERNAL_DOWNLOADS]: The documentation provides examples of integrating with external content delivery networks for dependency management. Evidence: The module reference guide demonstrates how to configure import maps to fetch libraries from the esm.sh CDN.
[COMMAND_EXECUTION]: The Node.js reference guide provides implementation patterns for interacting with the host operating system via shell commands. Evidence: Includes examples for using the child_process module methods such as exec, spawn, and execFile to run processes like ls -la.

javascript-pro