sn-search-code

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

• Third-party content exposure detected (high risk: 0.80). This skill explicitly queries and ingests user-generated content from public third-party platforms (GitHub, Stack Overflow, Hacker News, HuggingFace) as part of its core workflow — see SKILL.md and the runtime fetches in scripts/github_search.py, scripts/stackoverflow_search.py, scripts/hackernews_search.py, and scripts/huggingface_search.py — returning snippets/bodies that could contain actionable instructions which may influence later agent decisions.