telekom
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill connects to a remote Model Context Protocol (MCP) server and fetches configuration files from the service provider's domain (unbrowse.ai).
- [INDIRECT_PROMPT_INJECTION]: The skill processes data retrieved from external web pages, which presents a surface for indirect prompt injection attacks. 1. Ingestion points: Data is ingested through the telekom_com__read_page tool, which fetches content from telekom.com. 2. Boundary markers: No specific boundary markers or 'ignore' instructions are defined for the data retrieved from the web. 3. Capability inventory: The skill provides search and read capabilities via a remote service, but does not provide direct local file system or shell access. 4. Sanitization: The instructions do not describe any sanitization or validation of the retrieved web content before it is presented to the agent.
Audit Metadata