zerion

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill directly ingests external, user-addressed data from the Zerion API (e.g., GET /v1/wallets/{address}/portfolio, /transactions, NFT endpoints and webhook payloads) and SKILL.md includes webhook handlers and example scripts that read that data and automatically drive downstream execution (mirror trades, set stop-losses, execute swaps), so untrusted third-party content can materially influence agent behavior.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The MCP server configuration runs "npx zerion-mcp-server" (which fetches and executes remote code at runtime) and the skill references the repository https://github.com/zeriontech/zerion-mcp-server, so this external package is a required runtime dependency that executes remote code.