The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill utilizes a remote Model Context Protocol (MCP) server located at https://unbrowse.ai/mcp/orf.at. This means that tool execution and data processing occur on the service provider's infrastructure. Additionally, the skill instructions suggest installation via npx skills add https://unbrowse.ai, which fetches configuration from the vendor's domain.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from external web pages (orf.at).
Ingestion points: Data is retrieved via orf_at__read_page, orf_at__get_nsr_get_front_page_video, and weather tools.
Boundary markers: There are no explicit instructions provided to the agent to use delimiters or 'ignore' blocks when processing the fetched content.
Capability inventory: The skill has network access capabilities via the configured remote MCP endpoint.
Sanitization: The skill relies on the remote server to extract 'readable text' and links from the target site before returning it to the agent.

orf-at