recon-roofing

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly fetches remote debug logs and greps for DB_PASSWORD/DB_USER/DB_NAME and other PII, which instructs an agent/operator to retrieve and output secrets verbatim (high exfiltration risk).

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This document provides explicit, actionable instructions for unauthorized data exfiltration, credential theft, and remote code execution (uploading/using webshells) against roofing company websites, indicating clear malicious intent.

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

• Third-party content exposure detected (high risk: 0.85). SKILL.md’s runtime workflow uses curl to fetch arbitrary web content from outsider-controlled target domains (e.g., directory listings and debug.log/uploaded files) and then parses that fetched free text with grep/python3, which can include attacker/outsider-authored content.