skills/firecrawl/openclaw/weather/Gen Agent Trust Hub

weather

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is designed to fetch weather data from wttr.in, which is a well-known community service for terminal-based weather reports. This is a legitimate and expected behavior for a weather-related skill.
  • [COMMAND_EXECUTION]: The skill utilizes curl to perform network requests. These commands are statically defined to target the wttr.in domain, and their execution is necessary for the skill's primary function of retrieving weather information.
  • [INDIRECT_PROMPT_INJECTION]:
  • Ingestion points: The skill reads output from the external service wttr.in (SKILL.md).
  • Boundary markers: None explicitly defined in the instructions for the agent to distinguish between weather data and potential embedded instructions.
  • Capability inventory: Uses curl to fetch external data (SKILL.md).
  • Sanitization: None described for the received weather data.
  • Note: While the ingestion of external data theoretically presents an indirect injection surface, the use of a specialized weather service significantly minimizes the risk of receiving adversarial content.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 07:53 PM
Security Audit — agent-trust-hub — weather