The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the agent to fetch documentation and an index file (llms.txt) from neon.com using curl.
[INDIRECT_PROMPT_INJECTION]: The skill's primary function involves processing external documentation, which constitutes a potential attack surface for indirect prompt injection.
Ingestion points: Network requests to https://neon.com/llms.txt and specific documentation paths under https://neon.com/docs/.
Boundary markers: None specified for the ingested content.
Capability inventory: The skill utilizes curl for network operations to retrieve documentation.
Sanitization: No explicit sanitization or validation of the fetched markdown content is performed before it enters the agent's context.

using-neon