hunt-saml

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (critical risk: 1.00). This document contains explicit, actionable instructions and code examples for performing SAML/SSO attacks (XML Signature Wrapping, signature stripping, comment injection, XXE, NameID manipulation) aimed at account takeover and data exfiltration.

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill repeatedly shows workflows that embed raw SAMLResponse/base64 tokens directly into shell commands and HTTP parameters (e.g., echo "BASE64"/"BASE64_SAML" and re-encoding/POSTing the value), which requires the LLM to include sensitive assertion tokens verbatim in output.