X MCP guide

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

• Third-party content exposure detected (medium risk: 0.30). The workflow reads X (Twitter) posts, user profiles, mentions, DMs, and search results via Model Context Protocol tools, which ingest outsider-authored free text.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs the agent to clone an external helper repository from github.com/xdevplatform/xchat-grokbot-helper during runtime for X Chat functionality, constituting an unofficial operational dependency.

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

• Direct money access detected (medium risk: 0.30). The skill documents instructions and workflows for operating an X (Twitter) API MCP guide, including checking credit balances (get_usage_credits), estimating and tracking API call costs, purchasing or adding credits on console.x.com, and performing paid or free API queries. This involves managing API billing and paid calls, but does not perform direct financial transfers, charges, refunds, or trades itself; nor does it execute indirect operational workflows like submitting bills, invoices, or payroll on behalf of a system for financial settlement. Therefore, it constitutes an indirect/management scope regarding API usage costs rather than direct financial operations.