messari-deep-research
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses a shell script and the
mp(MoonPay) CLI tool to perform network requests, manage local configuration directories, and interact with blockchain payment systems. - [DYNAMIC_EXECUTION]: Short Python scripts are executed via
python3 -cto parse and extract specific fields from JSON data returned by API calls. - [INDIRECT_PROMPT_INJECTION]: The skill processes research reports fetched from
api.messari.io. This introduces a theoretical attack surface where malicious instructions could be embedded in the report content if the external provider were compromised. However, the use of a well-known industry data provider and the specific task of research report generation make this a standard operational risk rather than a targeted security flaw.
Audit Metadata