skills/qverisai/qverisbot/weather/Gen Agent Trust Hub

weather

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the curl binary to perform network requests. These commands are statically defined and target weather-related endpoints.\n- [EXTERNAL_DOWNLOADS]: The skill fetches weather information from wttr.in, which is a well-known and reputable service for terminal-based weather reports.\n- [PROMPT_INJECTION]: A surface for indirect prompt injection exists because the agent processes unverified data from a remote source.\n
  • Ingestion points: Data enters the context via the standard output of curl requests to wttr.in.\n
  • Boundary markers: None. External output is not wrapped in delimiters or accompanied by instructions to ignore embedded commands.\n
  • Capability inventory: The skill is permitted to run subprocesses (curl).\n
  • Sanitization: There is no evidence of validation or filtering applied to the remote data before it is presented to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 01:23 AM