internal-comms

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

• Third-party content exposure detected (high risk: 0.80). The skill's workflow and examples (examples/3p-updates.md "Tools Available" and examples/company-newsletter.md "Tools to use") explicitly instruct the agent to pull content from Slack, Google Drive, Email, Calendar and external press (public web/social content), so the agent will ingest untrusted/user-generated third‑party content that can influence its outputs.