tariff-guide
Pass
Audited by Gen Agent Trust Hub on Mar 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is dedicated to generating educational reference materials. Its operations are limited to data synthesis and static file generation based on public information.
- [PROMPT_INJECTION]: Analysis of the instructions found no attempts to bypass safety filters, extract system prompts, or override agent behavior.
- [DATA_EXFILTRATION]: The skill does not access sensitive local files (such as SSH keys or environment variables) and does not perform unauthorized network requests. Research is directed toward official government and trade databases.
- [REMOTE_CODE_EXECUTION]: There is no evidence of downloading or executing external scripts, binaries, or commands. The output is limited to static Markdown and HTML.
- [EXTERNAL_DOWNLOADS]: The skill specifically requires that generated HTML be fully self-contained with no external CSS, JavaScript, or font dependencies, which mitigates risks associated with third-party resource loading.
Audit Metadata