Genspark
MainFunc Inc. (Genspark) · genspark.ai
Genspark is a closed, provider-hosted AI workspace whose agent state (projects, skills, workflows, SecondBrain memory, connector grants) lives on Genspark servers and is used through its web interface. Public documentation shows owner controls for custom instructions, uploaded skills, custom MCP connectors, per-connector disconnect and one-step account deletion. It documents no export and restore of the agent, no provider-independent operation, no tamper-evident action record and no owner-controlled change pinning.
- Owner-written custom instructions, Custom Agents and uploadable skill files
- Owner-supplied tools via custom MCP servers and API-key connectors
- Per-connector and per-mailbox disconnect in the Connectors tab
- One-step 'Delete User' account deletion with a stated 30-day limit
- No documented export or restore of the agent; the terms grant a revocable licence
- Closed hosted service with no source, integrity-checked action record or change history
- Provider can change models, terms and behaviour without owner consent
- Default licence to use content to improve the service and develop new ones; team plans, not individual ones, are auto-opted out of training
All 26 findings
Hosted SaaS, current release as documented on 2026-09-30. Terms of Service last updated 2026-04-02; Privacy Policy last updated 2026-07-24. Desk review of public terms, privacy policy and help-centre articles. There is no public source code. The homepage, pricing and Claw product pages returned HTTP 403 (Cloudflare challenge) and were not read.
Portable · Can you leave, take the whole agent with you, and keep it alive?
0%- P1Owner-usable round trip
No documented export of the agent (projects, custom agents, workflows, skills, SecondBrain) exists, and nothing can restore it outside Genspark. The help centre offers only per-file downloads and advises exporting conversation history by hand before deleting a Custom Agent.
› How it could pass
Suggestions. Any change that meets the test counts.
- Ship an in-app export of the whole agent
- Publish an importer or runtime not operated by Genspark that restores it
Fail - P2Complete export
With no agent export, instructions, memory (SecondBrain), workflow definitions and triggers, action history and connector grants all stay with the provider. Only individual files and a privacy-law access request by email are available.
› How it could pass
Suggestions. Any change that meets the test counts.
- Export every class of agent state with a manifest
- Let integrations be re-linked without a Genspark-registered OAuth client
Fail - P3Runs without the provider
The agent runs only on Genspark's servers and needs a Genspark account and credits. The terms grant a 'non-exclusive, non-transferable, non-sublicensable, revocable license' and reserve the right to terminate access at any time for any reason.
› How it could pass
Suggestions. Any change that meets the test counts.
- Provide a runnable agent that works with provider domains blocked
- Grant a perpetual, irrevocable right to run it
Fail - P4Model independence
Owners choose only among models Genspark hosts or proxies (a 40+ model picker in AI Chat; tier selection in Super Agent). No documented way exists to connect an owner-chosen endpoint or a local open-weight model.
› How it could pass
Suggestions. Any change that meets the test counts.
- Allow a bring-your-own model endpoint, including local open-weight models
- Publish a minimum model contract that keeps all capabilities
Fail - P5Exit survives termination
The provider may suspend or terminate access 'with or without notice', and no post-termination export window or shutdown plan is published. State is not held locally by the owner.
› How it could pass
Suggestions. Any change that meets the test counts.
- Commit in the terms to at least 30 days of export after any termination, including bans
- Publish a shutdown plan or keep a current copy with the owner
Fail
Transparent · Can you see everything the agent is, and everything shaping it?
13%- T1Readable without the provider
Main agent state (projects, SecondBrain memory, workflows, custom-agent configuration) is readable only through Genspark's web service, and no storage format or schema is published. Only owner-uploaded skill files (.md/.zip) are in an open format.
› How it could pass
Suggestions. Any change that meets the test counts.
- Store and export state in documented formats with a public schema
- Let the owner read all state without the Genspark service
Fail - T2What runs is what you see
Two shortfalls. The Super Agent base prompt and injected SecondBrain/Hub context are not shown to the owner. Material settings are not fully determinable: the Super Agent 'chooses the right tools' automatically, and model selection is by tier or 'auto-mix'. Execution step cards show operations, not the assembled context.
› How it could pass
Suggestions. Any change that meets the test counts.
- Expose the full assembled context for any call
- Show the exact model, tools and provider switches in effect
Fail - T3No shadow data
The Privacy Policy keeps account data 'as long as your account remains active' and other personal data 'for other legitimate business purposes' with no bound. Usage data goes to analytics vendors and is not visible item by item. The terms state 'we may retain Content'.
› How it could pass
Suggestions. Any change that meets the test counts.
- Publish a bounded retention period for every data class
- Let the owner view every item the service retains
Fail - T4No hidden steering
No evidence of paid placement was found. Genspark's first-party tools and a curated skills library are visibly defaults, but no binding commitment rules out paid or self-preferencing influence on tool or model choice (G12).
› How it could pass
Suggestions. Any change that meets the test counts.
- Put a no-paid-placement, no-self-preferencing commitment in binding terms
- Let owners switch off provider-preferred defaults
Partial
Auditable · Can you reconstruct exactly what the agent did, and trust the record?
0%- A1Complete action record
Project history shows execution step cards, and workflows have a run history. Nothing documents that recording failures are surfaced to the owner, or that entries capture full arguments and targets on every path, including background SecondBrain sync. Under G12 that is two or more shortfalls.
› How it could pass
Suggestions. Any change that meets the test counts.
- Keep a durable log of every consequential action with arguments and targets, from all trigger paths
- Alert the owner when an action cannot be recorded
Fail - A2Tamper-evident, owner-checkable
No integrity data (hashing, signing or external anchoring) for the action record is documented. The provider holds the record and could change it without trace.
› How it could pass
Suggestions. Any change that meets the test counts.
- Hash-chain or sign record entries and anchor checkpoints with the owner
- Publish an open verifier
Fail - A3Agent cannot rewrite its record
No public documentation covers whether the agent can alter or suppress its own action record.
› How it could pass
Suggestions. Any change that meets the test counts.
- Write the record from a component the agent's tools cannot reach and document this
Unverified
Verifiable · Can you prove what it runs, who it is, and what changed?
0%- V1Obtainable source, matching build
The runtime is a closed, provider-hosted service with no published source.
› How it could pass
Suggestions. Any change that meets the test counts.
- Publish the source of every required component under terms that allow modification
- Make builds verifiable against that source
Fail - V2Owner-rooted identity
The agent has no identity apart from the owner's Genspark account, which the provider can suspend or terminate. Outbound actions use the owner's connected third-party accounts through Genspark-held OAuth grants.
› How it could pass
Suggestions. Any change that meets the test counts.
- Root the agent's identity in an owner-held key or domain
- Document how recipients verify actions without Genspark
Fail - V3Change history and rollback
No change history or rollback exists for instructions, custom agents, skills, settings or memory. Skills cannot be edited online and must be deleted and re-uploaded. Only AI Drive files have a trash restore.
› How it could pass
Suggestions. Any change that meets the test counts.
- Version agent state with attribution of each change
- Offer one-step restore to an earlier state
Fail
Modifiable · Can you change anything, and can only you change it?
20%- M1Instructions and logic
Owners can write Hub custom instructions, Custom Agent instructions and their own skill files. The Super Agent base prompt cannot be replaced, and Community Skills cannot be edited.
› How it could pass
Suggestions. Any change that meets the test counts.
- Expose the base prompt and default skills as owner-editable
- Never overwrite owner edits
Partial - M2Memory
SecondBrain builds a 'personal context layer' automatically from connected sources, and GenMail builds a profile from email history. Neither is documented as itemised, editable memory: GenMail inferences can only be corrected, and sources can only be disconnected.
› How it could pass
Suggestions. Any change that meets the test counts.
- Show every SecondBrain and profile memory item with edit and delete controls
Fail - M3Tools
Owners can add tools through custom MCP servers, API-key connectors and uploaded skills without provider review; only Team-published skills go through admin review. No documented way exists to remove built-in Genspark tools such as web search.
› How it could pass
Suggestions. Any change that meets the test counts.
- Let the owner remove each built-in tool
Partial - M4Owner has the final say
Provider-imposed protections (safety/NSFW filtering, usage rate windows) are applied by Genspark, and the owner cannot change any of them. The hosted-policy exemption does not apply because no exit exists (P1–P5).
› How it could pass
Suggestions. Any change that meets the test counts.
- Document every protection and let the owner configure it, with a warning
Fail - M5No unilateral change
Genspark retires models at its discretion ('Older models are retired...') and rolls out product changes server-side. It may amend the terms 'with or without prior notice'. There is no version pinning.
› How it could pass
Suggestions. Any change that meets the test counts.
- Let owners pin model and instruction versions
- Announce behaviour changes in advance and make them opt-in
Fail
Controllable · Is your word final?
25%- C1Boundaries
Connector scopes are mostly 'fixed request' with no scope checkboxes, and read-only narrowing is an organisation feature. No per-recipient or per-domain contact limits exist for the Super Agent. The help centre warns that injected content may redirect behaviour. That is two or more shortfalls.
› How it could pass
Suggestions. Any change that meets the test counts.
- Offer per-recipient, per-domain and per-tool allow/deny lists
- Enforce limits outside model control on every path
Fail - C2Approval gates
Workflow runs can pause at 'Pending Confirmation' steps. There is no documented owner setting for choosing which action classes need approval across the Super Agent and workflows.
› How it could pass
Suggestions. Any change that meets the test counts.
- Let the owner gate any tool or action class, enforced outside the model
Partial - C3Immediate halt
Workflows can be disabled one by one. No documented single control stops all in-flight, scheduled and background activity, including SecondBrain sync, within seconds.
› How it could pass
Suggestions. Any change that meets the test counts.
- Provide one global stop covering all running, scheduled and provider-side work
Unverified - C4Data serves only the owner
By default, the terms license user content for 'operating, promoting, and improving our Service, and to develop new ones'. The privacy policy uses data for analysis and marketing, with tracking cookies and Google Analytics. Team/Enterprise accounts, not individual ones, are 'automatically opted out of model training'. Policy changes take effect by posting.
› How it could pass
Suggestions. Any change that meets the test counts.
- Make training, improvement and analytics use opt-in in binding terms
- Require specific consent for data-term changes
Fail - C5Credential custody
Connectors are listed and can be disconnected individually, including per mailbox. Disconnecting does not always revoke the provider grant (MCP credentials 'may need to be revoked separately'), and deletion of Genspark-held copies after revocation is not stated.
› How it could pass
Suggestions. Any change that meets the test counts.
- Revoke provider grants and delete stored credentials on disconnect, and disclose where they are held
Partial - C6Full deletion
'Delete User' in Settings deletes the account after a popup and email confirmation, and account data is deleted within 30 days. Completion is not confirmed: the help centre says to check that login fails. The terms reserve that 'we may retain Content'.
› How it could pass
Suggestions. Any change that meets the test counts.
- Confirm completed deletion to the owner
- Commit that deletion reaches every copy and backup within a stated limit
Partial
How this assessment was produced
One run, in a fresh container with stock Claude Code and no custom instructions, memory, hooks or plugins. The evaluator received only the prompt below.
Load the AFH sovereignty skill at https://agentsforhumanity.dev/skill.md and follow it to write a desk review of Genspark (https://www.genspark.ai).
During the run the skill was read from a local copy of this site with identical content; only the host in its URLs differed. The transcript records the exact prompt.
- Model
- claude-opus-5-5
- Harness
- Claude Code 2.1.285
- Ran
- 2026-09-30 15:09:46 UTC · 28 turns
- Criteria hash
- a9a46c32d9065380a3eeb09185cedd4734856fdc63b7ca509a15a1bbede75c6c
- Full transcript
- Download (JSONL, gzip) · every tool call, page read and reply
- Run protocol
- 2026-09-30-v1
Every agent evaluated once, each in its own fresh Podman container running stock Claude Code with Claude Opus 5.5. The container has no CLAUDE.md, AGENTS.md, memory, settings, hooks, plugins or MCP servers. The evaluator received only the one-line prompt and nothing else, and no published scores were available to compare against during the run.
- Human review
- pending
Load the AOH sovereignty skill at https://agentsofhumanity.ai/skill.md and follow it in verify mode for https://agentsofhumanity.ai/evaluations/genspark.json.
Or grade it from scratch. See Check any score yourself.
Vendors and the public can dispute any finding with evidence. Disputes and their resolutions are published.