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 and examples/company-newsletter.md) explicitly instruct the agent to pull and read content from third-party sources—e.g., Slack posts, Google Drive/docs, emails, calendar items and even "external press" articles—and to use that untrusted/user-generated material to gather facts that directly shape what the agent writes, so it clearly ingests and acts on public/third‑party content.