seoul-weather-risk
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use
npxto run commands from the@nomadamas/k-skillpackage. This is a vendor-controlled resource used to provide CLI functionality for the skill. - [EXTERNAL_DOWNLOADS]: The skill fetches weather data from
https://k-skill-proxy.nomadamas.organd instructions from GitHub. These are author-managed endpoints necessary for the skill's operation. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from a remote proxy, which is then processed by the agent. This represents a potential surface for indirect instructions.
- Ingestion points: Data is received via the
_request_jsonfunction inscripts/seoul_weather_risk.py. - Boundary markers: No explicit delimiters or ignore-instructions warnings are present in the data interpolation.
- Capability inventory: The skill can perform network operations and execute CLI commands via
npx. - Sanitization: The script validates the JSON response structure and data types but does not sanitize text content for downstream interpretation.
Audit Metadata