analyzing-tls-certificate-transparency-logs

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

• Third-party content exposure detected (high risk: 1.00). The skill directly queries public Certificate Transparency sources (e.g., crt.sh via the search_crtsh_api function in scripts/agent.py and pycrtsh calls shown in SKILL.md, and optionally certstream in references) and ingests untrusted, public domain/certificate data which the agent parses and uses to drive detection and reporting decisions, so crafted third‑party inputs could influence its actions.