The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill connects to a remote Model Context Protocol (MCP) server at https://unbrowse.ai/mcp/kaspersky.com to execute its tools. This is the primary mechanism for the skill's functionality, routing requests through the developer's infrastructure to interact with the target website.
[INDIRECT_PROMPT_INJECTION]: The skill retrieves external data from kaspersky.com through search results and page content, which is then ingested into the agent's context.
Ingestion points: kaspersky_com__get_search_search and kaspersky_com__read_page tools.
Boundary markers: The skill does not explicitly define delimiters or instructions for the agent to ignore potentially malicious content embedded in the retrieved web data.
Capability inventory: The skill possesses network capabilities to communicate with the unbrowse.ai API and proxy requests to kaspersky.com.
Sanitization: No specific sanitization or filtering of the retrieved HTML or text content is described in the skill's instructions.

kaspersky