thegraph-token-mcp-skill

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md and usage patterns explicitly instruct the agent to probe and read help/operation responses from the public MCP endpoint https://token-api.mcp.thegraph.com/, meaning the agent ingests untrusted third‑party API output and uses it to decide operations and arguments.