xss-testing-burpsuite

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (critical risk: 1.00). The skill contains explicit exploit payloads and instructions for secret exfiltration (cookie theft, keylogger, screenshot/data POSTs to attacker servers) which constitute clearly malicious/deceptive content.

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

• Third-party content exposure detected (medium risk: 0.30). In scripts/agent.py, the runtime path main() → find_reflection_points(base_url, token) crawls and parses HTML returned from the user-supplied base_url to extract form actions/inputs and links (free-text HTML the LLM effectively ingests via resp.text).