lookup-bilateral-tariff
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides documentation for a trade tariff lookup service.
- [PROMPT_INJECTION]: The skill contains a 'Content safety' section that explicitly instructs the agent to treat API responses as data rather than instructions. While this contains phrases like 'ignore previous instructions', these are used as examples of malicious content to disregard, which is a defensive measure rather than an attack.
- [DATA_EXPOSURE]: The skill uses an API key via the 'X-WorldMonitor-Key' header, which is standard practice. It correctly instructs users to provide their own keys and uses a placeholder ('wm_012345...') in examples.
- [EXTERNAL_DOWNLOADS]: The skill connects to 'worldmonitor.app', which is the vendor's own domain. This is expected behavior for an API-based skill.
Audit Metadata