auditing-tls-certificate-transparency-logs

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly queries and ingests public, untrusted Certificate Transparency data from crt.sh and CT log servers (see SKILL.md "Query crt.sh" and scripts/agent.py functions query_crtsh/get_certificate_detail) and then uses those results to discover subdomains and generate/drive alerts and notifications, so third‑party content directly influences agent decisions and actions.