sorted-travel-weather

Pass

Audited by Gen Agent Trust Hub on Sep 20, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill connects to an external weather service at https://sorted.travel/mcp to fetch destination climate and forecast data. This communication is the core functionality of the skill and does not involve unauthorized data access or sensitive information exfiltration.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes weather data from an external API, which represents a theoretical attack surface for indirect prompt injection.
  • Ingestion points: External weather reports are retrieved via the get_destination_weather tool and incorporated into the agent's context.
  • Boundary markers: The instructions do not define specific delimiters or instructions to ignore potential commands embedded in the weather data.
  • Capability inventory: The skill has no capabilities to write to the file system, execute shell commands, or perform sensitive network operations beyond its own API communication.
  • Sanitization: There are no explicit sanitization or filtering steps for the incoming API data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 20, 2026, 06:21 PM
Security Audit — agent-trust-hub — sorted-travel-weather