recon-pools

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly extracts patterns like DB_PASSWORD and API_KEY from debug.log and prints them (grep/head), which requires the agent to read and output secret values verbatim, creating a high exfiltration risk.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This skill is intentionally malicious: it gives step-by-step recon and data-exfiltration techniques (directory listing/photo harvesting, debug.log download and credential/PII extraction, CORS abuse, portal discovery and default-credential checks) targeting SMB pool service/construction sites.

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

• Third-party content exposure detected (high risk: 0.85). SKILL.md’s required workflow uses runtime curl to fetch arbitrary target web pages and files (e.g., directory listings and wp-content/debug.log), which are outsider-authored free text from third-party websites and then parsed/printed into the agent’s execution context.