pp-quranku

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

• Third-party content exposure detected (high risk: 0.75). This skill’s workflow can fetch live web content from Quran.com at runtime (e.g., websearch, and related chapters/recitation/verses/surah that are “from Quran.com”), so outsider-authored free text from those pages can end up in the agent’s LLM context via the CLI’s --agent JSON output on stdout.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.80). The skill instructs installing required binaries by fetching and building remote Go modules (which will retrieve and execute remote code) via the targets github.com/mvanhorn/printing-press-library/library/education/quranku/cmd/quranku-pp-cli@latest and github.com/mvanhorn/printing-press-library/library/education/quranku/cmd/quranku-pp-mcp@latest, and the CLI is a required runtime dependency.