The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: Fetches writing guidelines and configuration from the official Vercel Labs GitHub repository. This is a recognized trusted source.
[PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because it retrieves and executes logic (rules and formatting instructions) from a remote URL. 1. Ingestion points: External writing guidelines fetched from raw.githubusercontent.com/vercel-labs (SKILL.md). 2. Boundary markers: Absent; the agent is instructed to obey all rules and instructions contained within the fetched document. 3. Capability inventory: The skill utilizes file system read access to process user documents and network access via WebFetch to retrieve remote content (SKILL.md). 4. Sanitization: No validation or sanitization of the remote content is performed before the agent follows its instructions.

writing-guidelines