daily-topic-selector

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

• Third-party content exposure detected (high risk: 0.90). The skill's runtime fetchers (see config/sources.yaml and scripts/run.py using src/fetchers: RSSFetcher, HTMLFetcher, JSONExtractor, APIFetcher and src/utils/http.HttpClient) pull and parse articles from many public sites (e.g., tldr.tech, Hacker News, Substack blogs, waitbutwhy.com, etc.) and then the Scorer and output generation (src/utils/scoring.py and src/utils/output_md.py) directly read that untrusted, user/public-generated content to rank/select and produce outputs, so third‑party content can materially influence the tool's decisions and results.