The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill requires the agent to author, review, and debug tour content stored in JSON files, creating an attack surface for indirect prompt injection.
Ingestion points: JSON tour files located in the public/intro/ directory.
Boundary markers: Absent; there are no explicit delimiters to separate tour body text from instructions during agent processing.
Capability inventory: The skill provides scripts for file system modification (writing to package.json and copying scripts) and source code analysis.
Sanitization: Absent; while the skill validates JSON schema, it does not sanitize the natural language fields for embedded instructions.- [COMMAND_EXECUTION]: The provided setup-intro.mjs script performs local file operations, including reading and writing package.json and copying the linting script into the host project. These actions are consistent with the skill's initialization purpose.- [EXTERNAL_DOWNLOADS]: The skill recommends the installation of the @devopsnext/starterkit-intro package and Playwright. These are recognized as legitimate dependencies from the skill's author and well-known service providers.

starterkit-intro