The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The fetch.py script downloads documentation files from raw.githubusercontent.com. This targets the well-known and official nuxt/ui repository, which is considered a safe source.
[COMMAND_EXECUTION]: The skill uses subprocess.run to execute curl for network requests. The command is constructed using a list of arguments rather than a shell string, which effectively prevents command injection from the input component name.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8) because it retrieves and displays untrusted content from the internet. * Ingestion points: Documentation content is fetched from the nuxt/ui repository in fetch.py. * Boundary markers: The skill prints the fetched Markdown content directly to the agent's context without any delimiters or instructions to ignore embedded commands. * Capability inventory: The skill allows shell command execution via the Bash tool and can write files to the local cache directory. * Sanitization: No sanitization, escaping, or validation is performed on the downloaded content before it is displayed to the agent.

nuxt-ui