weather-lookup
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided location data and external weather information, which represents an attack surface for indirect prompt injection. * Ingestion points: User research questions and weather data retrieved via tools in SKILL.md. * Boundary markers: The instructions do not specify delimiters to separate untrusted tool outputs from the agent's internal reasoning. * Capability inventory: The skill calls sandbase_call_tool to interact with external APIs. * Sanitization: No specific sanitization or filtering of the weather data is described.
Audit Metadata