{"version":1,"type":"story","url":"https://digestai.news/story/google-creates-empty-security-permission-for-ai-agents-on-android","json":"https://digestai.news/story/google-creates-empty-security-permission-for-ai-agents-on-android.json","markdown":"https://digestai.news/story/google-creates-empty-security-permission-for-ai-agents-on-android.md","slug":"google-creates-empty-security-permission-for-ai-agents-on-android","headline":"Google creates empty security permission for AI agents on Android","summary":"Google has added a new system permission called **EXECUTEAPPFUNCTIONS** to Android, designed to let autonomous AI agents invoke specific app functions without manual tapping. The permission lives inside the AppFunctionsManager framework and is currently reserved for first‑party Google software such as the Gemini assistant. While the cage is fully built and locked down, no third‑party agents have been granted access yet, so the feature remains empty for everyday users.\n\nThe approach aims to replace fragile screen‑tap automation with a hyperlink‑like shortcut that triggers a task directly, reducing breakage when apps change UI layouts. Google limits the permission to a small, in‑house tester group and has not announced a public rollout timeline. By establishing the security model early, Google hopes to avoid the risks of unrestricted agents that could read messages or move money without user awareness.\n\nIf developers eventually publish shortcuts and obtain the permission, Android could support more reliable, privacy‑preserving AI‑driven interactions across apps, extending the same capabilities already used by Gemini in Google’s own services.","keyPoints":["Google added a new Android permission (EXECUTEAPPFUNCTIONS) for AI agents to run app functions directly","The permission is currently limited to internal Gemini testers and contains no third‑party agents yet","Google’s early security cage aims to prevent unsafe, unrestricted AI actions on users’ phones"],"whyItMatters":"Establishing a controlled permission framework now prevents future privacy and security problems as AI agents become capable of acting autonomously on mobile devices.","category":{"slug":"agents","name":"Agents & Tools","url":"https://digestai.news/category/agents"},"entities":{"companies":["Google"],"models":["Gemini"],"people":[]},"firstPublishedAt":"2026-09-12T22:29:00Z","updatedAt":"2026-09-13T21:17:00Z","sourceCount":2,"hasPrimarySource":false,"sources":[{"outlet":"androidpolice.com","title":"Google built a security cage for AI agents on Android, but it's still empty","url":"https://androidpolice.com/android-ai-agent-permissions-cage-built-before-agents-arrive","publishedAt":"2026-09-12T22:29:00Z","type":"press","primary":false,"lead":true},{"outlet":"propakistani.pk","title":"Google Built a Secure Cage for AI Agents on Android","url":"https://propakistani.pk/2026/09/14/google-built-a-secure-cage-for-ai-agents-on-android","publishedAt":"2026-09-13T21:17:00Z","type":"press","primary":false,"lead":false}],"sourceNotes":null,"discussions":[],"thread":null,"cite":{"text":"Digest AI, \"Google creates empty security permission for AI agents on Android\", 12 September 2026, https://digestai.news/story/google-creates-empty-security-permission-for-ai-agents-on-android","publisher":"Digest AI","title":"Google creates empty security permission for AI agents on Android","datePublished":"2026-09-12T22:29:00Z","url":"https://digestai.news/story/google-creates-empty-security-permission-for-ai-agents-on-android"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}