x-twitter-data

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

• Third-party content exposure detected (high risk: 0.85). SKILL.md describes runtime calls to Twitter-related “read/search/timeline” tools (e.g., x_read/x_search/x_timeline), which necessarily ingest outsider-authored tweet/profile/article text returned by those external services into the agent’s LLM context.

MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).

• Direct money access detected (high risk: 1.00). The skill explicitly implements a pay-to-use API flow: it returns a 402 with an exact price, requires the client to pay and retry, and documents an AgentCash MCP call (mcp__agentcash__fetch) to perform the payment/signing. These are specific payment-execution primitives (a payment API/method), not generic request tooling, so the skill grants direct financial execution capability.