te-path-analysis

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill utilizes an official remote MCP server from Cisco ThousandEyes (api.thousandeyes.com), which is a well-known and trusted technology service.
  • [PROMPT_INJECTION]: The skill is subject to an indirect prompt injection surface as it processes external network telemetry to provide AI-generated explanations. 1. Ingestion points: Hop-by-hop path data, BGP route details, and network events retrieved from the ThousandEyes API. 2. Boundary markers: No explicit delimiters or instructions to disregard embedded commands in external data are present. 3. Capability inventory: Functional scope is limited to diagnostic analysis, path visualization, and reporting, with no high-risk system execution capabilities. 4. Sanitization: No explicit content validation or filtering of the external API responses is defined.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 12:32 AM