analyzing-certificate-transparency-for-phishing

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

• Third-party content exposure detected (high risk: 0.85). The workflow queries crt.sh and listens to Certstream at runtime, ingesting outsider-authored free text/prose from public CT log data (e.g., certificate common_name/name_value fields and related issuer strings) into the agent’s LLM context via the generated report text.