messari-funding-intel

Pass

Audited by Gen Agent Trust Hub on Mar 21, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the mp CLI tool, which is associated with the vendor 'moonpay'. It executes commands to check wallet balances and facilitate API requests via the x402 protocol. These actions are aligned with the skill's stated purpose of financial research and automation.
  • [EXTERNAL_DOWNLOADS]: The skill makes multiple requests to https://api.messari.io, a well-known and reputable service in the cryptocurrency sector. These connections are used exclusively to fetch structured financial data and perform AI-driven analysis using Messari's official endpoints.
  • [PROMPT_INJECTION]: In Step 5, the skill exhibits an indirect prompt injection surface. It ingests untrusted data from the Messari API (steps 1-4) and interpolates it directly into a system/user prompt for an AI model ({step1_output}, etc.). There are no boundary markers or instructions to ignore embedded commands within the ingested data. Although the data comes from a reputable source, the lack of sanitization and delimiters presents a theoretical risk if the external API content were to be compromised or intentionally malicious.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 21, 2026, 10:25 PM