The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: Fetches latest writing guidelines from Vercel Labs' public GitHub repository.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by fetching rules from an external URL and instructing the agent to apply them to user content.
Ingestion points: The command.md file fetched from the vercel-labs/writing-guidelines repository via WebFetch.
Boundary markers: Absent; there are no instructions to wrap or isolate the fetched guidelines using delimiters.
Capability inventory: The skill can read local files and perform network fetches.
Sanitization: Absent; the skill does not specify any validation or sanitization of the fetched content before processing it.

writing-guidelines