wordpress-penetration-testing

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt contains numerous examples that instruct embedding API tokens, passwords, and credentials directly into commands and payloads (e.g., --api-token YOUR_API_TOKEN, --http-auth admin:password, set PASSWORD jessica, xmlrpc brute-force entries), which would require the LLM to output secret values verbatim.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The content explicitly instructs how to perform credential brute-force, remote code execution, install backdoors (reverse shells, a webshell plugin with system($_GET['cmd'])), credential/exfiltration techniques, and detection-evasion (proxies/Tor/throttling), which are clear, high-risk malicious behaviors despite a stated testing purpose.

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to fetch and parse open/public site content (e.g., using curl and WPScan against arbitrary targets such as http://target.com/wp-json/ai/v1/, feed pages, readme files, and plugin/theme files) and to act on that data to choose scans and exploits, so untrusted third‑party content can directly influence tool usage and actions.