story-short-write

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md explicitly requires automatically scanning and reading third‑party reference directories (e.g., 拆文库/{书名}/ and {短篇标题}/对标/{书名}/) and instructs running /story-short-analyze and /story-short-scan to load/analyze public platform novel samples, so it will ingest untrusted, user-generated web content and use it to drive writing decisions.

MEDIUM W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).

• Hidden Unicode characters detected (1 type(s) found)