komoot
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references and connects to a remote Model Context Protocol (MCP) server at
https://unbrowse.ai/mcp/komoot.com. This URL belongs to the skill vendor and is used to provide the tool definitions and execution environment. - [INDIRECT_PROMPT_INJECTION]: The skill acts as a surface for indirect prompt injection by design, as it retrieves and processes content from external pages on komoot.com. * Ingestion points: The
komoot_com__read_pageandkomoot_com__get_1_355235_103_796882_elementstools ingest data from komoot.com into the agent context. * Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore potentially malicious content embedded in the retrieved web data. * Capability inventory: The skill enables network interaction with the komoot.com domain through the vendor's proxy service. * Sanitization: There is no evidence of content sanitization or filtering before the data is presented to the agent.
Audit Metadata