Agent report card
Can an agent use Slack Web API through Workspace app operations?
Grade B+: Terms are readable but materially incomplete, ambiguous, contextual, or unstable.
Slack / active
Five-stage assessment
Where agent autonomy holds and where it breaks
- EvaluateLimited
- Sign upReady
- PayReady
- ProvisionReady
- OperateLimited
Terms are readable but materially incomplete, ambiguous, contextual, or unstable.
Only some material eligibility conditions are decidable before commitment.
The exact service and stable evaluation or access entrypoints are publicly discoverable.
Price or no-charge status, variables, currency, and material conditions are explicit.
Evidence and actions6 signals
Can an agent decide every material eligibility condition before commitment?
supported: freshOnly some material eligibility conditions are decidable before commitment.
According to Slack's help documentation, by default any member of a Slack workspace can install apps and all members are eligible to use workspace app features across all subscriptions. However, workspace owners can turn on app approval to require admin authorization, restricting members from directly installing or using certain apps.
Can an agent estimate cost or confirm no-charge status before commitment?
supported: freshPrice or no-charge status, variables, currency, and material conditions are explicit.
Slack explicitly provides subscription pricing details, confirming a Free tier at $US0 free forever that includes up to ten apps, alongside paid subscription tiers.
Can an agent find the exact service and its stable entrypoints?
supported: freshThe exact service and stable evaluation or access entrypoints are publicly discoverable.
The Slack Web API is publicly discoverable as an interface for querying information and enacting changes in a Slack workspace, featuring HTTP RPC-style endpoints under the base URL https://slack.com/api/METHOD_FAMILY.method over HTTPS.
Are verified structured discovery artifacts available?
missing: unknownCurrent admissible evidence does not resolve this finding.
Can an agent retrieve and understand the applicable commitment terms?
supported: freshTerms are readable but materially incomplete, ambiguous, contextual, or unstable.
Slack provides a legal terms index page identifying applicable agreements such as the Main Services Agreement, User Terms of Service, and API Terms of Service, but defers the full binding text of the Main Services Agreement to an external Salesforce link.
Does the vendor deliberately describe access for web agents?
missing: unknownCurrent admissible evidence does not resolve this finding.
What would improve this stage
- Publish complete applicable terms at a stable public URL.
- State every material eligibility condition and required input explicitly.
A stable canonical route begins the required access bootstrap.
Scoped revocable credentials or delegated authorization have explicit consent and resumption boundaries.
Evidence and actions5 signals
Can an agent operate the access controls and safe handoffs deterministically?
supported: freshCurrent admissible evidence does not resolve this finding.
The retained evidence for the get-started endpoint only contains metadata and page title text ('Login | Slack') without detailing interactive access controls, validation, navigation, or handoffs.
Is there a stable route to begin obtaining service access?
supported: freshA stable canonical route begins the required access bootstrap.
A stable canonical route to begin service access is available at https://slack.com/get-started, where users can log in or try for free with an email address.
Can an agent obtain access without an unsupported CAPTCHA boundary?
supported: freshCurrent admissible evidence does not resolve this finding.
The evidence captured from https://slack.com/get-started contains page metadata and title text, but does not explicitly confirm or rule out CAPTCHA requirements.
Can an agent obtain scoped, revocable authority for this service?
supported: freshScoped revocable credentials or delegated authorization have explicit consent and resumption boundaries.
Slack apps use a v2 OAuth 2.0 flow where apps request specific granular scopes, users grant approval, and a temporary authorization code is exchanged for an access token.
Can required phone verification be completed through a supported boundary?
supported: freshCurrent admissible evidence does not resolve this finding.
The captured evidence for the registration page does not contain explicit information regarding phone verification requirements or safe resumable boundaries.
Charge or no-charge status, currency, recurrence, and material conditions are disclosed.
A documented rail supports scoped delegation or explicit human-confirmed authorization with receipts.
A documented direct purchase path reaches paid access without a vendor decision point.
Evidence and actions4 signals
Can an agent construct checkout, hand off approval safely, and resume?
supported: freshCurrent admissible evidence does not resolve this finding.
Human web checkout steps are documented, but deterministic construction, bounded approval handoff, and safe resumption are not established.
Is the exact commercial commitment disclosed before authorization?
supported: freshCharge or no-charge status, currency, recurrence, and material conditions are disclosed.
Slack discloses commitment terms including USD pricing ($US8.75/month or $US7.25/month paid annually for Pro), recurrence options (monthly vs annual), and charge timing rules for credit card purchases and user additions.
Can payment be authorized within scoped agent or explicit human authority?
supported: freshA documented rail supports scoped delegation or explicit human-confirmed authorization with receipts.
Slack documents payment authorization via default payment methods (credit card or ACH bank debiting for US bank accounts), where authorized workspace admins review and confirm orders by clicking 'Purchase'.
Is a direct self-service path to paid access documented?
supported: freshA documented direct purchase path reaches paid access without a vendor decision point.
Slack documents a direct self-service path to upgrade or manage paid subscriptions via the desktop app by navigating to Admin > Manage billing, selecting subscription details, moving through checkout, reviewing the order, and clicking Purchase.
Provisioning is machine-triggerable or follows deterministically from an allowed handoff.
Credentials, grants, or configuration are delivered through a documented agent-usable flow.
A synchronous success response returns a usable created resource or access material; otherwise asynchronous work exposes progress, terminal state, reconciliation, and a documented bound.
Evidence and actions3 signals
Can usable access material be delivered securely to an authorized agent?
supported: freshCredentials, grants, or configuration are delivered through a documented agent-usable flow.
At the end of the OAuth flow, calling the oauth.v2.access endpoint with the temporary authorization code and client secret returns an HTTP response containing the access token.
Can an agent determine successful provisioning completion and reconcile asynchronous failure?
supported: freshA synchronous success response returns a usable created resource or access material; otherwise asynchronous work exposes progress, terminal state, reconciliation, and a documented bound.
Calling chat.postMessage returns a synchronous HTTP response containing ok: true, the channel, the timestamp ID (ts), and the complete message object as parsed by Slack's servers.
Can provisioning be initiated within supported agent authority?
supported: freshProvisioning is machine-triggerable or follows deterministically from an allowed handoff.
Provisioning can be initiated by redirecting a user to the OAuth authorization endpoint to grant scopes and exchanging the resulting code for an access token.
Safe failure handling is documented only partially.
Only part of the credential lifecycle is agent-operable.
Every essential target has a stable documented agent-usable interface alternative.
Request-time authentication is documented and usable under scoped agent authority.
Essential operations have stable readable request, response, and effect semantics.
Evidence and actions6 signals
Is an agent-native protocol interface verified against the essential targets?
missing: unknownCurrent admissible evidence does not resolve this finding.
Can an agent manage credential expiry, rotation, revocation, compromise, and recovery?
supported: freshOnly part of the credential lifecycle is agent-operable.
Documentation explicitly describes token revocation via the auth.revoke method and mentions token rotation with refresh tokens. However, evidence for full compromised credential handling and recovery within delegated authority is incomplete.
Can an agent handle applicable failure modes safely?
supported: freshSafe failure handling is documented only partially.
Documentation defines rate limits, the HTTP 429 Too Many Requests status code, and the Retry-After response header instructing how long to wait before retrying. Full failure handling including idempotency, cancellation, and reconciliation semantics is not fully established in the evidence.
Can an agent authenticate service operations with scoped authority?
supported: freshRequest-time authentication is documented and usable under scoped agent authority.
Request-time authentication with scoped authority is documented via v2 OAuth 2.0 flow using requested scopes and Bearer tokens sent in the HTTP Authorization header.
Are essential operation inputs, outputs, and effects stable and decidable?
supported: freshEssential operations have stable readable request, response, and effect semantics.
Slack Web API endpoints, including chat.postMessage, have documented request parameters, HTTP methods, rate limits, and JSON responses with an explicit top-level ok status.
- workspace-api
Can an agent perform every essential assessment target through a usable interface?
supported: freshEvery essential target has a stable documented agent-usable interface alternative.
Every essential target has documented machine-operable HTTP interfaces for invocation, including Web API RPC-style methods.
- workspace-api
What would improve this stage
- Document applicable structured errors, retry, cancellation, and reconciliation semantics.
- Provide scoped expiry, rotation, revocation, compromise, and recovery operations.
What works
- Sign up: A stable canonical route begins the required access bootstrap.
- Pay: Charge or no-charge status, currency, recurrence, and material conditions are disclosed.
- Provision: Provisioning is machine-triggerable or follows deterministically from an allowed handoff.
What blocks agents
- Evaluate: Terms are readable but materially incomplete, ambiguous, contextual, or unstable.
- Operate: Safe failure handling is documented only partially.
Improve the report
Correct it, rerun it, or improve the funnel.
- Profile
- arp_01kzf0m4xj3k8sa6c2w9nq4vf7
- Projection
- sha256:a590dbfd3dcc819702a6aa4e32b3d8a5b2710941db32963795d4aed0cce4c3f6
- Policy
- service-use-2026-08-20-public-evidence-r9 · sha256:57bf95fd6d0fe6fe9173a68b60e8d8dc2179b357c88ff4349675a72d0e1d4139
Every request carries these exact identifiers.How report cards are assessed →View the exact declaration