saudi-weather

Pass

Audited by Gen Agent Trust Hub on Nov 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes shell commands to retrieve information from a remote API.\n
  • Evidence: Several curl commands are used in SKILL.md to call the Open-Meteo weather service.\n- [EXTERNAL_DOWNLOADS]: Fetches current weather and air quality conditions from Open-Meteo's public API endpoints.\n
  • Evidence: Downloads data from api.open-meteo.com and air-quality-api.open-meteo.com.\n- [DATA_EXFILTRATION]: Performs network operations to external services not included in the default whitelist.\n
  • Evidence: Network calls to the Open-Meteo API domains in SKILL.md.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests and displays data from external sources, which could lead to unauthorized instruction execution if the source is compromised.\n
  • Ingestion points: Responses from Open-Meteo API endpoints (SKILL.md).\n
  • Boundary markers: Absent; no specific delimiters or ignore-instructions are used for the external data.\n
  • Capability inventory: The skill provides the agent with access to execute network requests via curl.\n
  • Sanitization: Absent; no specific filtering or validation logic is defined for the API data content.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 11, 2026, 04:09 PM