accelint-english-manager

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill explicitly requires preserving "config keys" and quoted/technical text verbatim, so if a user-provided secret (API key, token, password) is part of the text the LLM is instructed to output it unchanged, creating an exfiltration risk.

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

• Third-party content exposure detected (medium risk: 0.30). The required runtime workflow is a content-first editor that takes outsider-authored text directly from the user request (the prompt’s provided paragraphs/sentences) and rewrites/audits it without needing to select from a trusted external repository.