The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes local initialization scripts and manages dependencies via the shell.
Found in references/local-prototype-preflight.md: Instructs the agent to run a bootstrap script using node /absolute/path/to/plugins/product-design/scripts/bootstrap-prototype.mjs --dest /absolute/path/to/new-prototype.
Found in references/local-prototype-preflight.md: Directs the agent to run npm install within the project directory.
Found in SKILL.md: Requires running a 'preflight script' from the user-context skill when local shell access is available.
[EXTERNAL_DOWNLOADS]: The skill utilizes package managers to fetch external software components.
Found in references/local-prototype-preflight.md: The use of npm install implies downloading dependencies from the public npm registry.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection from untrusted external inputs.
Ingestion points: As noted in SKILL.md and references/critical-overrides.md, the skill reads data from external product URLs, Figma files, and user-provided screenshots.
Boundary markers: Absent. The instructions do not define delimiters or provide warnings to the agent to ignore instructions contained within the ingested external data.
Capability inventory: The skill has the ability to execute shell commands (node, npm) and perform deployments to services like Vercel.
Sanitization: Absent. There is no mention of filtering or escaping content derived from external design assets or URLs.

product-design-share