story-long-scan

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). Repository documentation explicitly instructs using fake/paid "假追" metrics to manipulate platform recommendation systems, which is deliberate abusive behavior (fraudulent manipulation of ranking/metrics).

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

• Third-party content exposure detected (medium risk: 0.30). Required runtime workflow uses scraper scripts (e.g., scripts/qidian-rank-scraper.js, scripts/fanqie-rank-scraper.js, scripts/qimao-rank-scraper.js, scripts/jjwxc-rank-scraper.js, scripts/ciweimao-rank-scraper.js) to fetch and ingest free-form outsider-authored text from third-party platform pages (book titles/author names/intro/metadata) into the LLM during analysis.