fullstack-debugger

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt includes multiple examples that embed API keys/tokens directly in commands and client constructors (e.g., Authorization: Bearer YOUR_TOKEN, createClient('URL','KEY')), which would require substituting real secret values verbatim if the agent executed or generated those commands.

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

• Third-party content exposure detected (high risk: 1.00). The skill runs network fetches against public Cloudflare Worker endpoints (e.g., scripts/check-cors.sh and scripts/inspect-cache.sh call https://jb4l-meeting-proxy.erich-owens.workers.dev) and queries Supabase tables including user-generated tables like "forum_posts" and "journal_entries" via scripts/check-rls.js and WebFetch, meaning it ingests untrusted, public third-party content and interprets it as part of its diagnostics.