performing-http-parameter-pollution-attack

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This skill explicitly documents and automates HTTP Parameter Pollution techniques (including concrete payloads and examples for OAuth redirect hijacking, payment manipulation, and WAF evasion) that enable credential theft, token/external redirect exfiltration, and financial fraud — behaviors that are clearly usable for deliberate malicious activity.

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly fetches and parses arbitrary public web content—see scripts/agent.py (test_parameter_precedence, test_hpp_payloads, test_waf_bypass using requests.get against user-supplied URLs) and SKILL.md curl examples against http://target.com—and uses those untrusted responses to determine parameter precedence, anomalies, and WAF bypasses, so third-party content can materially influence agent actions.