TiDB X

TiDB X — object-storage-native distributed SQL for AI agent workloads. Use when building agent memory, context storage, multi-agent coordination, Web3 indexi...

What to check before installing: - Verify the skill source (the files reference a GitHub raw URL and a third-party API). Install only if you trust that source. - The SKILL.md examples call curl, jq, and the mysql client but the skill metadata lists no required binaries; ensure jq/mysql are present or update the metadata. - The provisioning API creates ephemeral DB instances and returns credentials (MYSQL_PWD). Anything your agent writes to that DB will be stored on a third-party service — do not send sensitive data (PII, secrets, PHI) unless you trust the provider and account isolation. - The provisioning endpoint appears unauthenticated; confirm billing/claim flow to avoid unexpected charges if instances are converted to permanent accounts. - If you don't want the agent to create remote resources automatically, restrict autonomous invocation for this skill or run it in a sandboxed agent environment. If you can confirm the upstream endpoints (zero.tidbapi.com and claim URLs) are legitimate and are comfortable with remote storage of agent data, the skill is coherent for its purpose; otherwise treat it as risky and avoid installing.

Type: OpenClaw Skill Name: tidb-x Version: 1.0.0 The skill bundle is designed to teach an AI agent about TiDB X and facilitate its use. It includes instructions for provisioning a temporary database via a `curl` command to `zero.tidbapi.com` and connecting to it using standard `mysql` client commands. While this involves external network requests and handling database credentials, these actions are explicitly stated, aligned with the skill's purpose, and do not show any evidence of malicious intent such as unauthorized data exfiltration, persistence mechanisms, or prompt injection attempts to subvert the agent's core directives. The `curl` commands for self-installation from GitHub are also standard practice.