customs-trade-compliance
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from untrusted external sources, such as commercial invoices, packing lists, and supplier questionnaires. It provides templates in
references/communication-templates.mdto interpolate this data into agent-generated communications.\n - Ingestion points: Data enters the agent's context through external document processing and ERP interaction as described in
SKILL.mdandreferences/decision-frameworks.md.\n - Boundary markers: The instructions do not include delimiters or specific guidance for the agent to ignore instructions that might be embedded within the external trade data.\n
- Capability inventory: Although the skill contains no scripts, the agent is expected to interact with sensitive regulatory systems like ACE, CHIEF/CDS, and various customs portals, which could be abused if an injection is successful.\n
- Sanitization: There are no instructions for the agent to sanitize, escape, or validate the content of interpolated variables before use.\n- [NO_CODE]: The skill consists entirely of Markdown documentation and reference files. There are no Python scripts, Node.js packages, binary executables, or shell commands that could be used for direct command execution or remote access, which limits the overall risk profile.
Audit Metadata