ci

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches CI job logs from external sources (e.g., GitHub Actions via "gh run view --log" in references/analyzing-failures.md) and injects those logs into downstream tooling/subagent prompts (the ci-cd-fixer prompt="...エラーログ: {error_log}" in SKILL.md), so untrusted user-generated content could influence tool behavior.