The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill fetches markdown documentation and reference guides from the vendor's base URL. This content is used to inform the agent's understanding of available API endpoints and workflows at runtime.
[PROMPT_INJECTION]: An indirect prompt injection surface is present due to the dynamic ingestion of remote content. * Ingestion points: Documentation is fetched from <base_url>/docs/md/reference and <base_url>/docs/md/guide and read by the agent. * Boundary markers: The skill does not implement specific delimiters or 'ignore' instructions when processing the fetched markdown, which could allow embedded malicious instructions to influence the agent. * Capability inventory: The skill has the capability to perform authenticated network requests and read local configuration files. * Sanitization: No validation or sanitization is performed on the fetched documentation content before the agent interprets it.

ledda