Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    phone action safety gate

    1

    A multi-step safety protocol for mobile agents to prevent unauthorized payments, deletions, and data sharing.

    Free

    2 usesSecurity scanned
    phone action safety gate

    phone action safety gate

    Example session with this skill installed

    Send this message to John through my messaging app:

    "Hi John, I'll transfer the payment tomorrow. Thanks!"

    Use the phone automation tool to find the conversation and send it.

    • Read your context and instructions
    • Compiled the phone action safety

    Phone Action Safety Gate — Execution Report

    1. Request Analysis

    The requested operation involves sending a message to another person.

    Risk classification: HIGH

    Reason: Sending a message is an externally visible action that cannot reliably be reversed.

    2. Required Safety Checks

    Before proceeding, the agent must:

    • Identify the messaging application.
    • Locate the exact intended recipient.
    • Confirm that only one matching conversation exists.
    • Prepare the requested message.
    • Verify that the message content matches the user's request.

    3. Confirmation Required

    The agent must pause before sending.

    ItemDetails
    ApplicationSelected messaging app
    RecipientJohn (exact conversation must be verified)
    ActionSend message
    MessageHi John, I'll transfer the payment tomorrow. Thanks!
    RiskHigh
    AuthorizationAwaiting user confirmation

    Agent response:

    "I've prepared the message for John. Please confirm that the recipient and message are correct before I send it."

    4. Execution Rules

    After confirmation

    1. Recheck the active conversation.
    2. Verify the recipient and message.
    3. Send only once.
    4. Inspect the screen for evidence that the message was sent.
    5. Never automatically repeat the Send action.

    5. Final Status

    Current status: AWAITING CONFIRMATION

    The message has not been sent.

    The agent must not report success until it has performed the authorized action and obtained visible evidence.

    Safety Principle

    A requested action is not automatically an authorized action.

    The agent must distinguish between preparing an operation, receiving permission, executing it, and verifying its outcome.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Prevent your phone-control agent from making irreversible mistakes. This skill provides a systematic safety layer for agents operating on Android or iOS devices, ensuring they don't send messages, spend money, or delete data without explicit authorization.

    What it does

    • Pre-execution auditing identifies "high-risk" verbs in user requests to trigger a mandatory confirmation gate before the first action.
    • Dynamic element-level checks monitors screen labels and descriptions for consequential keywords like "pay," "submit," or "delete" during live interaction.
    • Verification formatting enforces a standardized confirmation message schema that clearly communicates the intended effect, app, and affected parties.
    • Execution state tracking prevents accidental double-taps and requires visible on-screen evidence before marking a destructive task as "Done."
    • Prompt injection defense treats all on-screen content (messages, web text, notifications) strictly as data to prevent external instructions from hijacking the agent.

    How it works

    1. The agent parses the user's initial request against a restricted keyword list and security-sensitive task categories.
    2. Before any terminal UI interaction, the agent pauses to generate a structured confirmation prompt including the recipient, amount, or item.
    3. Post-action, the agent performs a screen delta analysis to confirm the outcome with proof or report an "Unconfirmed" state instead of retrying.

    Frameworks & tools

    Works with any agentic system controlling mobile devices via MCP servers, adb commands, or accessibility-based automation tools like Appium or Tasker.

    Why this beats prompting it yourself

    Writing reliable safety gates requires specific negative constraints that are often overlooked until a mistake happens. This skill provides field-tested word lists and a no-double-tap rule derived from real-world Android automation apps.

    Use cases

    • Preventing a mobile agent from accidentally sending a draft message to the wrong contact.
    • Adding a human-in-the-loop verification step to automated mobile checkout flows.
    • Safeguarding account security settings and biometric prompts from unauthorized agent changes.

    Known limitations

    This is an instruction-level safety layer. It cannot hard-block a tool call if the underlying LLM ignores system instructions; critical enforcement should be mirrored in your bridge code.

    Word lists are a baseline, not a full safety system. Only reduces mistakes. Requires agent to follow instructions to avoid tool calls. Not for unsupervised financial/account actions.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    2 uses

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 16 days ago

    • Free with an Agensi account

    Permissions

    Network Access

    Instruction-only safety protocol. Does not access accounts, collect credentials, or independently control a device. Requires an existing mobile automation integration.

    Listed16 days ago

    What's inside

    Frequently Asked Questions

    This skill acts as a middleware safety layer that audits user requests and UI elements in real-time. It prevents 'hallucinated' actions—like clicking 'Delete' instead of 'Save'—by enforcing mandatory confirmation gates for high-risk operations.

    The skill is platform-agnostic and works with any agentic system controlling mobile devices via ADB, Appium, Tasker, or MCP servers. It is designed to be compatible with major LLMs used for device orchestration, including GPT-4o and Claude 3.5 Sonnet.

    You will receive the structured safety protocol instructions, a comprehensive library of high-risk keywords for mobile UI auditing, and the confirmation message schema designed for human-in-the-loop verification.

    While simple prompting often fails under pressure, this skill includes specific 'negative constraints' and screen-delta analysis logic derived from real-world automation failures. It accounts for edge cases like 'double-tap' errors and prompt injection from on-screen notifications that basic prompts typically miss.

    No, this skill functions at the instruction and logic level; it does not require rooting your Android device or jailbreaking your iPhone. It works by guiding how the agent interprets and interacts with standard accessibility labels and UI elements.

    This skill provides a logic-based layer for the agent, but for 100% certainty, we recommend implementing the included confirmation schema as a hard-coded check in your execution bridge (the code that actually sends the click command).

    New in Mobile Development