granola-ci-integration

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

• Third-party content exposure detected (high risk: 0.90). The skill ingests user-generated Granola meeting notes via the Zapier "New Note Created" trigger (see SKILL.md Step 1 and references/implementation.md where noteContent = inputData.note_content) and parses that untrusted content to create GitHub issues, Linear tasks, and trigger workflows, so third-party content can materially influence agent actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.80). The skill sends runtime requests to https://api.github.com/repos/your-org/your-repo/dispatches and example Zapier webhook URLs like https://hooks.zapier.com/hooks/catch/YOUR_HOOK_ID which trigger remote execution (GitHub Actions and Zapier workflows) and are required for the integration to operate, so they constitute runtime external dependencies that execute remote code.