The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash(cmd:*) tool to execute several system commands, including npm install, npx prettier, find, and chmod u+w. These are used to manage dependencies, search for configuration files, and ensure the agent has write permissions to format code files.
[EXTERNAL_DOWNLOADS]: The skill downloads and installs Node.js packages (prettier, husky, lint-staged) from the official npm registry. These are well-known developer tools and the downloads occur during the standard setup and formatting workflow.
[INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it is designed to read and process external project files which may contain untrusted content.
Ingestion points: Project source files (e.g., .js, .ts, .json, .css, .md) are identified using find and processed by formatting tools as described in SKILL.md and references/implementation.md.
Boundary markers: Absent; the instructions do not specify the use of delimiters or warnings to ignore instructions embedded within the processed code files.
Capability inventory: The skill possesses extensive system access capabilities including Bash(cmd:*), Write, and Edit as defined in the YAML frontmatter of SKILL.md.
Sanitization: Absent; no evidence of content filtering or validation is present before the agent processes or reformats the files.

code-formatter