recipe-forward-labeled-emails

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The recipe instructs the agent to fetch a Gmail message and then construct a send command that embeds the "Original Message Body" verbatim, which forces the LLM to handle and output potentially sensitive message contents (including secrets) in generated commands — an exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.85). This workflow uses the gws-gmail skill to list and then fetch Gmail message content (gws gmail users messages get), which will ingest outsider-authored email body text from other senders into the agent context for forwarding.