recon-automotive-dealers

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs fetching and printing site artifacts (debug.log, WP REST user output, uploaded credit applications) that can contain API keys, cookies, passwords, or PII, which would require the LLM/agent to include secret values verbatim in its output.

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 1.00). These URLs include an explicit attacker-controlled domain (https://evil.com) and WordPress upload/xmlrpc endpoints that can host or enable uploading of arbitrary files — common vectors for distributing malware.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The document is an explicit, targeted reconnaissance playbook instructing discovery and automated extraction of PII, credentials, inventory (VINs), and other sensitive data from car-dealer websites—demonstrating clear malicious intent for data exfiltration and abuse.

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

• Third-party content exposure detected (high risk: 0.85). This skill’s runtime workflow uses curl to fetch outsider-authored free text from public web targets (e.g., crt.sh JSON and wp-json user listings, debug.log, plugin readme.txt, inventory/credit-application pages), which is then parsed/printed and thus becomes LLM-readable context if the agent ingests command output.