Kiro CLI

# Fix list: Kiro CLI

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/kiro-cli, the October 2026 research run, assessed 8 October 2026. Grade C, 59.9 out of 100.

This is everything the published grade says the listing lacks, the biggest possible gain to the total first. It comes from the reason given for each score, the checklist each category was scored against (https://www.anchorterminal.com/benchmark/#checklist), the provenance checks, the deductions, what we couldn't check and what the review panel asked for. A fix counts at the next check, once it's public.

For a coding agent working on Kiro CLI: work through the items below in the product, its docs and its public pages. Each category gives the reason for its score, with the points each checklist item earned, and the checklist itself, so the gap is the items that earned less than their points. Change the product, not the wording, and keep a note of what you changed and where it's published.

## 1. Reliability, 57 out of 100, up to 8.6 more on the total

Why it scored 57: Local-package reading, the same as the other closed-source harnesses. An install script that verifies SHA-256 checksums, a .deb, an AppImage and a PowerShell script, with macOS, Windows 11 and Linux (glibc 2.34 or newer, or musl) stated (20). No public CI or test suite, since the source isn't published and the GitHub repository is an issue tracker (0). 1,401 open issues in the shared Kiro tracker, 428 labelled cli, with 96 cli issues opened and 69 closed in the 30 days to 8 October, area labels, a triage label and stale-issue automation. Open reports from the last week include a `--no-interactive` run that never exits after a refusal (12). A dated changelog for every release and a breaking-change table with a migration guide for V3, which runs beside 2.x until the user opts in, though 2.24.0 stopped loading project `.env` files in a minor version (10). 2.28.0, with V3 still an early release (15).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability):

Hosted APIs, MCP servers, models and platforms.

- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).
- 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so.
- 15, rate limits documented with numbers.
- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.
- 10, an SLA published for any paid tier.
- 10, the surface agents use is generally available, not beta or preview.

Local packages, SDKs, frameworks and stdio MCP servers.

- 20, installs from an official package with supported runtimes stated.
- 25, a public CI and test suite, passing on the default branch.
- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).
- 15, semver discipline and breaking changes called out in a changelog.
- 15, version 1.0 or later, or declared stable.

Protocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors.

## 2. Payments & pricing, 40 out of 100, up to 7.5 more on the total

Why it scored 40: Harness reading of the published rubric, scored on the Kiro subscription the CLI needs. No payment protocol (0). Plan prices, the $0.04 credit price and per-model credit multipliers are public without a login (20). Kiro Free has 50 credits a month, and the pricing page asks for a card only on upgrade (20). A person signs in through a browser or device flow, and the API key for headless runs is created by hand at app.kiro.dev on a paid plan (0).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-payments):

The published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).

- 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which.
- 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for "contact sales" or prices behind a login.
- 20, a free tier or trial that doesn't need a card.
- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).

Payment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied.

Open-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol.

## 3. Security & auth, 66 out of 100, up to 6 more on the total

Why it scored 66: Framework reading (telemetry defaults, approvals, guardrails, sandboxing), five lines. Telemetry and content collection are on by default for Free and individual accounts, each with a documented opt-out, and enterprise users are opted out. API keys are long-lived and revocable with no scopes, and administrators must switch key generation on (14). Deny over ask over allow across six scopes, hard-coded denies on Kiro's own settings paths, workspace trust and a managed policy that fails closed. There is no local sandbox in the CLI, and AWS says managed policies are client-enforced and can be circumvented (16). An untrusted workspace doesn't load its agents, steering, MCP configuration or skills, compound shell commands are split before matching, and the MCP page warns that servers run outside any sandbox (11). Enterprise prompt logging to the customer's S3 bucket covers the CLI, with daily activity reports and OpenTelemetry export, and individuals have local logs only (11). AWS vulnerability reporting with a HackerOne disclosure programme, CVEs published in security bulletins with credit to reporters, ISO/IEC 27001:2022 scope and HIPAA eligibility. kiro.dev has no security.txt and the one on aws.amazon.com expired on 24 September 2026 (14).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-security):

- 0 to 30, the credential model. 30 for OAuth 2.1 with scopes, or scoped and revocable keys with rotation. 20 for plain revocable API keys. 10 for one all-powerful key. 10 off when a secret can travel in a URL query string as a documented option.
- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.
- 0 to 15, prompt-injection posture where the tool returns untrusted content (documented mitigations or guidance). A tool that returns no untrusted content gets 10.
- 0 to 15, audit logs or per-call visibility for the operator.
- 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public.

Models are read for retention, whether API data trains models (and whether that's off by default), zero-retention options and certifications. Frameworks for telemetry defaults, approval hooks, guardrails and sandboxing.

## 4. Agent ergonomics, 67 out of 100, up to 5.4 more on the total

Why it scored 67: Framework reading, adapted to a harness driven by a pipeline. `--trust-tools` limits approved tools, `disabledTools` removes MCP tools per server, tool search loads MCP tools on demand, and custom agents carry their own tool set (20). Compaction and a workflow timeout (`KIRO_HEADLESS_WORKFLOW_TIMEOUT_SECS`, six hours by default) exist, but no cap on turns or run time for a plain headless run was found (10). Distinct exit codes for MCP startup failure and a missing agent, `--require-mcp-startup`, and a final interruption record in stream-json, with exit 1 for everything else (14). Sessions are saved every turn, with `--resume`, `--resume-id` and checkpoints with rewind (15). No SDK. The programmatic interfaces are the headless command and the ACP server, and a headless run needs a paid-plan API key and explicit trust flags (8).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics):

- 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries).
- 20, pagination, filtering and output-size controls.
- 20, actionable, documented error responses, codes and messages an agent can recover from.
- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.
- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.

Models are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs.

## 5. Schema & documentation, 79 out of 100, up to 3.4 more on the total

Why it scored 79: Framework reading. A command reference, a settings reference, an exit-code page and a documented rule format for permissions, plus the Agent Client Protocol methods the CLI implements. No published schema for the stream-json events was found (14). kiro.dev/llms.txt indexes every docs page and each has a Markdown twin, though robots.txt disallows both for crawlers (10). The permissions page states the defaults, what each preset allows and when to pick it, and that headless runs treat ask as deny (16). Rules are validated, an unknown preset rejects the session request, and a malformed managed policy fails closed (12). CI examples, exit codes 0, 1, 3 and 4 and hook exit codes are documented, but code 1 covers every other failure (12). Versioned releases with a dated changelog and a 2.x reference kept beside V3 (15).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-schema):

APIs and MCP servers.

- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).
- 10, llms.txt or Markdown docs served for agents.
- 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference.
- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.
- 0 to 15, examples and documented error responses.
- 15, versioning and a public changelog.

Models are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference.

## 6. Transparency & trust, 67 out of 100, up to 2.9 more on the total

Made of editorial 62, provenance 72.

Why it scored 67: Proprietary, with clear terms. The licence page puts the CLI under the AWS Customer Agreement and the AWS Intellectual Property Licence, where the Amazon Q Developer CLI it replaced was Apache 2.0 (15). The data protection page says what is stored for Free, individual and enterprise users, names US East (N. Virginia) for storage, lists inference regions, and gives 60 days for Free Tier abuse detection and 30 days for some models. It agrees with sections 50.3 and 50.14 of the AWS Service Terms. No general retention period for stored content was found (22). Classic sessions carry a deprecation notice and V3 has a breaking-change table and migration guides, but no deprecation policy or removal dates were found (10). Telemetry types are listed and `telemetry.enabled` turns them off, with collection on by default (15).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency):

- 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms.
- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).
- 0 to 20, a deprecation policy or notices with dates.
- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).

The other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two.

Provenance checks not met in full (half of this category, computed from checked facts):

- Domain age: kiro.dev, registered 2019-03-01 (7 years) (11 of 15)
- Status page: not found (0 of 10)
- security.txt: not found (0 of 10)

## 7. Maintenance & community, 73 out of 100, up to 2.4 more on the total

Why it scored 73: 2.28.0 on 5 October 2026 (30). At least 11 minor versions and their patches between 26 August and 5 October (20). A public issue tracker with area labels and triage automation, 69 cli issues closed against 96 opened in 30 days, and a Discord server. We didn't establish how many replies come from staff (14). No SDK and no registry entry. The ACP server is kept current, with a migration guide for clients moving to V3 (6). Closed source, so no CI or dependency health to read. The installer verifies checksums (3).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance):

- 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older.
- 20, at least three releases or dated changelog entries in the last 90 days.
- 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15.
- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).
- 10, package health, current dependencies and CI.

Models are read for deprecation notice periods and model churn rather than release counts.

## Deductions

Each comes off the total. A fixed and documented problem counts for less at the next check.

- 2026-08-04. CVE-2026-18656 and CVE-2026-18657 (bulletin 2026-074-AWS), an uncontrolled search path on Windows let a planted executable in a crafted project directory run when a user opened it. Kiro CLI for Windows before 2.10.0 and Kiro IDE 1.0.0 to 1.0.212. Fixed and published with credit to the reporters, inside six months (https://aws.amazon.com/security/security-bulletins/2026-074-aws/). -2
- 2026-05-22. CVE-2026-9255 (bulletin 2026-035-AWS), content piped to kiro-cli on stdin could answer the tool approval prompt, so a local actor could run tools and shell commands without the user's approval. kiro-cli before 1.28.0. Fixed and published, inside six months (https://aws.amazon.com/security/security-bulletins/2026-035-aws/). -2

## What we couldn't check

What we couldn't read counted as absent. Publishing it on a page a plain HTTP fetch can read (not only in a browser) lets the next check count it.

- unchecked: whether Kiro has a public status page or appears on the AWS Health Dashboard. None is linked from kiro.dev or its docs, and status.kiro.dev didn't answer
- unchecked: the event schema of `--output-format stream-json`. The headless page describes the format and no schema was found
- unchecked: how many replies in the GitHub issue tracker come from AWS staff, and the Discord server
- unchecked: releases before 26 August 2026. Only the first page of the CLI changelog was read, so the 90-day count is a lower bound
- unchecked: the AWS sub-processor list and the Data Privacy FAQ the data protection page links to
- Whether a paid bug bounty covers Kiro. The AWS security.txt points to a HackerOne vulnerability disclosure programme, and its Expires date of 24 September 2026 had passed
- robots.txt on kiro.dev disallows /llms.txt and the Markdown twins for crawlers, while llms.txt tells agents to fetch them. We read the HTML pages for the docs
- The headless page documents `--trust-tools` for V3 runs while the V3 page says permissions.yaml replaces the trust flags. We didn't run either engine
- The CLI overview page calls ACP the Agent Communication Protocol, and the ACP page calls it the Agent Client Protocol

## Weaknesses

- Free and individual paid accounts have content used for service improvement, including model training, unless they opt out
- Closed source since it replaced the Apache 2.0 Amazon Q Developer CLI, with no public CI or test suite
- API keys for headless runs need a paid plan, are long-lived and carry no scopes
- No local sandbox in the CLI, and AWS says its managed permission policies are client-enforced and can be circumvented
- Two CVEs in 2026 (CVE-2026-9255 in May, CVE-2026-18656 and CVE-2026-18657 in August), both fixed

## What costs an agent a turn today

The notes we give agents before they call it. Each one is a workaround an agent shouldn't need.

- Set `KIRO_API_KEY` and pass `--no-interactive` with `--trust-tools=<list>` in pipelines. Keep `--trust-all-tools` for disposable environments
- Pass `--require-mcp-startup` when a run depends on MCP tools. Without it a failed server is logged and the run continues
- Pass `--no-interactive` whenever input is piped from a source you don't control, and run 2.10.0 or later on Windows
- Run `kiro-cli settings telemetry.enabled false` and turn off content collection on Free and individual plans. Both are on by default
- Export variables in the shell before starting. Since 2.24.0 a project `.env` file is no longer loaded into sessions, MCP servers or tools

## When it's done

Send what changed and where it's published as a dispute (https://www.anchorterminal.com/builders/#disputes, or `POST https://www.anchorterminal.com/api/v1/contact` with `"kind": "dispute"`). Disputes are answered in public, and the listing is checked again by the same checklist. Paying for an audit or a listing claim changes nothing here.