idor-testing

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The prompt instructs intercepting and modifying authenticated HTTP requests (including Cookie/session headers) and shows examples that embed session tokens in request headers, so an agent following it would likely need to handle and output secret session values verbatim, creating an exfiltration risk.

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

• Third-party content exposure detected (high risk: 1.00). SKILL.md explicitly requires a "Target Web Application" URL and instructs capturing and analyzing live HTTP requests/responses (see Inputs/Prerequisites and Core Workflow: Reconnaissance, Detection Techniques, Exploitation with Burp Suite), so the agent would fetch and interpret arbitrary third‑party web content that can directly influence subsequent actions.