ln-514-test-log-analyzer

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly supports querying an arbitrary Loki HTTP endpoint (SKILL.md Phase 1: "LOKI_URL env var or tools_config.md observability section" and references/analyze_test_logs.py's collect_loki which uses --loki-url/LOKI_URL), ingesting remote log entries (untrusted/user-generated) that are parsed and used to classify errors and drive reporting/decisions.