password-reset-poisoning

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly directs the agent to collect, save, and include "new credentials or tokens found" and token values in its return summary/evidence, which forces the LLM to handle and output secret values verbatim.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The document is an explicit, actionable guide for stealing password reset tokens and achieving account takeover (host header poisoning, email/CRLF injection, referer exfiltration, token brute-forcing and response manipulation), which enables deliberate malicious abuse if used without authorization.