waf-bypass-methodology

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The document explicitly details techniques to evade WAFs and perform exploitation (double/multi encoding, HTTP smuggling/chunking, method overrides, parameter pollution) and even shows a concrete webshell upload example (), indicating clear intent to enable remote code execution, backdoors and system compromise.

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

• Third-party content exposure detected (high risk: 1.00). This skill explicitly instructs the agent to send requests to arbitrary external "TARGET" URLs and analyze response headers/bodies (see "Phase 0: WAF 识别" with curl examples in SKILL.md), so it ingests untrusted third-party content that directly influences subsequent bypass actions.