mitm-find-idor

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs the agent to analyze a mitmproxy capture and to include request/response snippets and reproducible test commands (e.g., curl with Cookie/Authorization headers), which may require copying session tokens or API keys verbatim from log.txt, creating an exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly requires analyzing a mitmproxy dump file (log.txt) captured from arbitrary network traffic, meaning the agent ingests untrusted third-party web content from outside sources and uses it to guide tests and actions (grep/curl commands), so that content could materially influence behavior.