import-export-trade-data-leads
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to add an MCP server using the command
claude mcp add --transport http manypi https://mcp.manypi.com/mcp -s user. This command installs a third-party tool from the vendor's domain to provide additional data processing capabilities.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted trade data from external sources, which could contain malicious instructions designed to influence the agent's behavior.\n - Ingestion points: National customs declarations, bill of lading datasets, and port cargo records.\n
- Boundary markers: The instructions lack explicit delimiters or warnings to ignore instructions embedded within the processed records.\n
- Capability inventory: The agent uses external tools to query, filter, and summarize data based on the provided JSON brief.\n
- Sanitization: No specific sanitization or filtering logic is mentioned for the incoming shipping manifest or trade data.
Audit Metadata