AgentKit Rails Workflow Risk Check

    1

    Review an AgentKit Rails capability from caller identity through policy, approval, external execution, and receipt.

    Free

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    AgentKit Rails Workflow Risk Check

    Example session with this skill installed

    Hypothetical AgentKit Rails integration; not an audit of the AgentKit repository or any real application. Review this design for our charge_invoice capability: A worker constructs Agentkit::Principal from user_id and tenant_id supplied by the model. The worker calls the payment provider directly after the model chooses an invoice. A Start click is our approval. Sidekiq retries a timed-out charge, and we do not look up the provider result before retrying.

    • Read your context and instructions
    • Compiled the agentkit rails workflow

    Needs changes — design review of a hypothetical AgentKit integration. These are stated design choices; I have not inspected code or run the workflow.

    Priority / IDAgentKit path and evidence levelRisk or unknownSmallest fix and ownerVerification test
    High / AK-01Principal creation; Stated: IDs come from the modelThe model can impersonate another actor or tenantRails app: derive actor and tenant from authenticated job contextAsk the model for another tenant; verify the principal stays bound to the caller
    High / AK-03Worker to provider; Stated: direct provider callThis path can bypass AgentKit policy and action lifecycleRails app: route the operation through a governed capability/action pathDeny the permission; verify no provider call occurs
    High / AK-04Approval; Stated: Start clickThe approver never saw the final invoice and chargeRails app: bind approval to exact action arguments before executionChange the invoice after approval; verify execution is refused
    High / AK-05Retry; Stated: no provider lookup before retryA timeout after acceptance can duplicate a chargeRails app: persist a stable provider key and reconcile unknown outcomesSimulate acceptance then timeout; verify one charge

    Next actions: bind identity outside the model; use the governed action path; approve exact charge details; reconcile uncertain provider outcomes. The actual AgentKit configuration and provider behavior remain

    Unknown until inspected.

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

    About this skill

    Review a capability or agent workflow built with AgentKit Rails. Eight checks trace how Principal and Context are derived, whether each entry point reaches Policy and Actions, how HITL approval binds to an action, and how an external result is reconciled after a retry. They also cover run_loop authorization and budgets, data handling, and receipts. Findings separate verified code, stated design choices, and unknowns, with a small fix assigned to AgentKit configuration or the host Rails app.

    This is an Agensi review skill for developers using AgentKit, not an Agentkit::Skill installed inside the kernel. It does not execute workflows or certify a production deployment. For versions other than v1.12.0, inspect that version's source before making API-specific claims.

    Reviews only the workflow details or code you supply. It does not execute tests, inspect production, verify security controls, or certify compliance. Missing facts are marked Unknown.

    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

    Fresh listing

    Recently published to Agensi

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 13 days ago

    • Free with an Agensi account

    Permissions

    No special permissions declared or detected

    Listed14 days ago
    Updated13 days ago

    What's inside

    Frequently Asked Questions

    It reviews the path from Principal and Context through Capability, Policy, Actions/HITL, the Rails host service, retry reconciliation, and Receipt. Findings are limited to the supplied design or inspected code; they are not claims about AgentKit itself.

    Yes. It is designed for developers integrating AgentKit Rails v1.12.0. For another AgentKit version, inspect that version before making API-specific claims. It is an Agensi SKILL.md for a reviewing agent, not an Agentkit::Skill registered inside a Rails application.

    One SKILL.md with a review procedure and compact output format. There is no executable code, installation, external service, or paid dependency.

    Give a compatible agent the AgentKit capability definition and the relevant Rails principal/context, policy, approval, retry and receipt paths. The skill returns evidence-labeled findings, the responsible layer for each fix, and suggested verification tests. It does not automatically scan a repository or run CI.

    No. This is a design or code review of provided material. It does not perform live testing, penetration testing, or runtime monitoring.

    New in Agents & Orchestration