gws-gmail-read

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md explicitly instructs the agent to "Read a message and extract its body or headers" (examples use gws gmail +read --id ), meaning it fetches and interprets Gmail message bodies—untrusted, user-generated third-party content—that could contain instructions influencing later actions.