analyzing-certificate-transparency-for-phishing

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly queries public Certificate Transparency sources (crt.sh via https://crt.sh in SKILL.md and scripts/agent.py and listens to Certstream at wss://certstream.calidog.io) and ingests untrusted certificate subject/issuer/domain data which the agent parses and uses to trigger alerts, risk scores, and follow-up actions, so third‑party content can materially influence behavior.