hunt-forgot-password

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly directs the agent to look for reset tokens/links in API responses and to reuse/submit those tokens (e.g., in token replay tests), which requires reading and outputting secret token values verbatim and is therefore high exfiltration risk.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This document explicitly instructs how to enumerate accounts, extract or replay reset tokens, and brute-force or flood reset endpoints to achieve account takeover — high-risk guidance for malicious abuse or automated exploitation.

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

• Third-party content exposure detected (medium risk: 0.30). SKILL.md describes an autonomous testing workflow that requires POSTing to the forgot-password/reset endpoints and ingesting the responses (including error bodies and any reset token) from arbitrary outsider-chosen inputs like emails, so outsider-authored free text is consumed via request parameters and the resulting response text.