recon-dentists

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This document is an explicit reconnaissance and attack playbook targeting dental practices that details methods to discover PHI, enumerate users, exploit vulnerable plugins, achieve RCE, and exfiltrate sensitive patient data—clearly malicious and intended for abuse.

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

• Third-party content exposure detected (high risk: 0.70). This skill’s required workflow uses runtime HTTP requests (e.g., curl to https://crt.sh/?q=...&output=json and to target site paths like /wp-content/plugins/.../readme.txt), which can ingest outsider-authored free text (public web content and arbitrary third-party site responses) into the agent’s LLM context if the tool outputs are passed through.