simplified-technical-english

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill mandates preserving protected literals verbatim (code fences, commands, endpoints, identifiers, schema keys, placeholders, etc.), which forces the model to reproduce any embedded secrets (API keys, tokens, passwords) present in the source text.

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

• Third-party content exposure detected (medium risk: 0.30). SKILL.md’s required workflow ingests user-supplied “exact selected text” at runtime for rewrite/audit (plus optional local reference-backed checks), so outsider free text is directly consumed to produce rewritten output or findings.