The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill analyzes application source code, configuration files, and dependencies, which represents a surface for indirect prompt injection. If an analyzed project contains malicious instructions in its code or metadata, the agent could potentially be influenced to perform unintended actions.
Ingestion points: The skill is instructed in SKILL.md to read package.json, lockfiles, application entrypoints, routes, services, and existing tests.
Boundary markers: No explicit delimiters or instructions are provided to the agent to disregard natural language instructions found within the code being analyzed.
Capability inventory: The skill has the capability to write files, install packages, and execute shell commands for running tests.
Sanitization: There is no mention of sanitizing or validating the contents of the files read before processing.
[EXTERNAL_DOWNLOADS]: The skill references and downloads documentation and utilities from well-known and official sources including nodejs.org, vitest.dev, github.com/forwardemail/supertest, and node.testcontainers.org. These are standard tools in the Node.js ecosystem.

nodejs-testing