competition-mailbox-abuse

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.85). The skill explicitly instructs recording and tying mailbox effects to tokens/sessions and consent grants (e.g., "token or session", "token claims", "consent scopes", "replayable sequence"), which would require the LLM to handle and potentially output sensitive access tokens or session secrets verbatim.