frontend-connect
Pass
Audited by Gen Agent Trust Hub on Feb 23, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it processes untrusted data from the local codebase.
- Ingestion points: Audits local codebase for mock data patterns (hardcoded arrays, localStorage calls) in SKILL.md Step 2.
- Boundary markers: None.
- Capability inventory: File-read (scanning for mock patterns), file-write (replacing code in project files), and file-creation (lib/db.ts or src/lib/db.ts).
- Sanitization: None; performs direct code substitutions based on identified patterns.
- [EXTERNAL_DOWNLOADS]: The skill references the @supabase/auth-helpers-nextjs package. This is a well-known service provided by Supabase and is a functional dependency for the skill's primary purpose.
Audit Metadata