The Agent Skills Directory

[COMMAND_EXECUTION]: The skill is designed to interact with the local repository by executing various maintenance and installation scripts. Specifically, it uses node to run scripts/ci/catalog.js, scripts/install-plan.js, and scripts/install-apply.js. It also utilizes standard CLI tools like find for discovery, rg (ripgrep) for searching content, and npm for running audits and tests. These scripts are local to the project and used for managing the repository lifecycle.
[INDIRECT_PROMPT_INJECTION]: The skill's core functionality involves reading and searching through files in the repository to provide up-to-date answers. This creates a surface for indirect prompt injection if the files being processed contain malicious instructions.
Ingestion points: The agent reads file content from SKILL.md, README.md, and other project files discovered via find and searched via rg.
Boundary markers: The instructions do not specify the use of delimiters or boundary markers to separate file content from the agent's internal instructions.
Capability inventory: The skill has the ability to execute local scripts (via node and npm), search the filesystem, and write installation plans.
Sanitization: There are no explicit instructions to sanitize or filter the content read from files before it is processed by the agent.

ecc-guide