weather

Pass

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION] (SAFE): The skill uses curl to retrieve weather information. This is the primary function of the skill and does not involve piping output to a shell or executing arbitrary commands.\n- [EXTERNAL_DOWNLOADS] (SAFE): Network requests are made to wttr.in and api.open-meteo.com. These are well-known public weather services. The download of a PNG to /tmp/weather.png is a standard use of a temporary directory for non-sensitive data.\n- [INDIRECT_PROMPT_INJECTION] (LOW): \n
  • Ingestion points: The skill reads weather reports from wttr.in and JSON from open-meteo.com.\n
  • Boundary markers: No specific delimiters or instructions are provided to the agent to ignore instructions embedded in the weather data.\n
  • Capability inventory: The skill uses curl for data retrieval and file writing to /tmp. It does not have high-privilege capabilities.\n
  • Sanitization: No sanitization is performed on the incoming weather data. While this presents a theoretical surface for indirect prompt injection (e.g., if a weather service returned a malicious string), it is a standard risk for any data-fetching skill and is mitigated by the benign nature of the tool and the primary use case.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 18, 2026, 11:59 AM