tidb-query-tuning

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

• Third-party content exposure detected (high risk: 0.90). The skill's AGENTS.md and workflow explicitly require mining GitHub issues using scripts/generate_tidb_issue_experiences.py (via the gh CLI and network access) to fetch and ingest public, user-generated GitHub issue/PR content into the agent's corpus, which the agent is expected to read and use to decide fixes—this clearly exposes it to untrusted third-party content from GitHub.