migrate-bluejay

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill prompt instructs the agent to ask the user for API keys and then embed them directly into curl headers (-H "X-API-Key: <COVAL_KEY>"), exposing the raw secrets in the LLM's context and output.

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

• Third-party content exposure detected (medium risk: 0.30). The skill reads data from the Bluejay API, which constitutes third-party outsider-authored content ingested at runtime.