vercel

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt includes explicit examples that embed bearer tokens directly in request headers (curl -H "Authorization: Bearer YOUR_ACCESS_TOKEN") and similar patterns that would require or encourage the LLM to insert user-provided secret values verbatim into generated commands or code, creating an exfiltration risk.