The Agent Skills Directory

[COMMAND_EXECUTION]: The bundled script scripts/validate_design_md.mjs executes shell commands using Node.js spawnSync. It specifically runs the npx command to interface with the @google/design.md CLI tool.
[EXTERNAL_DOWNLOADS]: The skill uses npx to download and run the @google/design.md package from the NPM registry. This package is maintained by a trusted organization.
[REMOTE_CODE_EXECUTION]: The skill executes remote code by pulling the linting tool from a public registry at runtime. This is standard behavior for the tool's intended purpose.
[PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it ingests and interprets findings from untrusted DESIGN.md files.
Ingestion points: File content from DESIGN.md is read by the agent and processed by the validation script.
Boundary markers: The skill does not define specific delimiters or warnings to ignore instructions that might be embedded within the files being validated.
Capability inventory: The agent can execute a local script which has the ability to run subprocesses.
Sanitization: The validation script passes file paths to spawnSync as an array of arguments, which prevents common shell-based command injection attacks.

design-md-validator