CrawlCheck

Registry · Capabilities · aivisibilitystudio.com

Capability registry

What aivisibilitystudio.com declares an agent can do

Measured 2026-11-16 16:11 UTC from the declarations the site publishes (record b8q8bi46n0). Each capability is shown as declared, under the policy class that decides whether anything may call it, beside what a call observed.

12declared
4public read-only
2called and verified
0declared ≠ observed
a2a, agent_skill, mcp, openapiprotocols
Public read-only: 4Identity and accounts: 2Unknown: 5Metadata: 1
Public read-only 4 · Identity and accounts 2 · Unknown 5 · Metadata 1

Declared versus observed

CapabilityPolicy classDeclaredObserved
getAgentApiIndex
openapi · GET · https://aivisibilitystudio.com/api/agent/v1/
Public read-onlyHTTP GET with no declared security
auth: none · required inputs: 0
behavior verified HTTP 200 · application/json
getStudioProfile
openapi · GET · https://aivisibilitystudio.com/api/agent/v1/profile
Identity and accounts
never called automatically
its name contains “profile”
auth: none · required inputs: 0
not attempted
classed identity_or_account: only read-only public actions are ever called
listPublicResources
openapi · GET · https://aivisibilitystudio.com/api/agent/v1/resources
Public read-onlyHTTP GET with no declared security
auth: none · required inputs: 0
behavior verified HTTP 200 · application/json
searchPublicResources
openapi · GET · https://aivisibilitystudio.com/api/agent/v1/search
Public read-onlyHTTP GET with no declared security
auth: none · required inputs: 1
not attempted
needs 1 required input: nothing is invented to fill them
getAgentApiHealth
openapi · GET · https://aivisibilitystudio.com/api/agent/v1/health
Public read-onlyHTTP GET with no declared security
auth: none · required inputs: 0
not attempted
outside the per-scan call budget (2 GETs, 1 MCP tool)
get_studio_profile
mcp · https://aivisibilitystudio.com/mcp
Identity and accounts
never called automatically
its name contains “profile”
auth: unknown
not attempted
classed identity_or_account: only read-only public actions are ever called
find_public_resources
mcp · https://aivisibilitystudio.com/mcp
Unknown
never called automatically
its effect is not stated in the declaration
auth: unknown
not attempted
classed unknown: only read-only public actions are ever called
explain_studio_capability
mcp · https://aivisibilitystudio.com/mcp
Unknown
never called automatically
its effect is not stated in the declaration
auth: unknown
not attempted
classed unknown: only read-only public actions are ever called
list_public_resources
mcp · https://aivisibilitystudio.com/mcp
Unknown
never called automatically
its effect is not stated in the declaration
auth: unknown
not attempted
classed unknown: only read-only public actions are ever called
explain-studio-services
a2a
Unknown
never called automatically
its effect is not stated in the declaration
auth: none
not attempted
classed unknown: only read-only public actions are ever called
find-public-evidence
a2a
Unknown
never called automatically
its effect is not stated in the declaration
auth: none
not attempted
classed unknown: only read-only public actions are ever called
research-ai-visibility-services
agent_skill · https://aivisibilitystudio.com/.well-known/agent-skills/research-ai-visibility-services/SKILL.md
Metadata
never called automatically
an instruction file an agent reads; not an operation
auth: none
not attempted
metadata: describes a surface, is not itself an action

Where the declaration and the call disagree

None: every capability that was called answered as declared.

Signed certificate

This page’s rows, signed by the observer’s Ed25519 key: every capability’s id, endpoint, safety class, policy class and observed state, the declaration hashes and the record’s sealed manifest. The certificate is derived from the record alone, so the same record always yields the same id.

certificate_id ccap1:98e276ed2e2e977317d4ebff35432706ce88794414f808f2760ed25ea9146a06
alg Ed25519 · kid 1hHmE3fo1rg5Ig70wuFtJ5wBc7G-sUTgUJkxyPWFRps
sig _lYs_NP6uNUx-3VqaYSnegtvGZ_i735LoiV9qSP29J8mb3TMIgUo3pVj9WToyUH9UWYpkrud2fOwscEP3uSYDw

The certificate as JSON · verify it now · the key directory · machine-readability certificate

To verify it yourself: SHA-256 the certificate object as canonical JSON (keys sorted, no whitespace); the hex digest must equal certificate_sha256 and the id; then check the Ed25519 signature over "crawlcheck-capability-certificate-v1\n" followed by that hex digest, with the key in the directory whose RFC 7638 thumbprint is the kid.

Policy classes

Policy classCalled automatically?Rule
Public read-only
public_read_only
yes, to verifyMay be called without credentials. CrawlCheck calls it only to check the declaration: GET with no input, on the scanned origin.
Authenticated read-only
authenticated_read_only
neverNever called by CrawlCheck. An agent needs the user's own credentials and consent.
Reversible write
reversible_write
neverNever invoked automatically. Needs the owner's written authorisation and a test account.
Irreversible write
irreversible_write
neverNever invoked automatically. Deletes or changes something that cannot be undone.
Financial
financial
neverNever invoked automatically. Moves money or creates a charge.
External communication
external_communication
neverNever invoked automatically. Sends a message, email or notification to someone.
Identity and accounts
identity
neverNever invoked automatically. Creates, signs in to or changes an account or credential.
Unknown
unknown
neverNever invoked. Its effect cannot be read from the declaration, so it is treated as the riskiest case.
Metadata
metadata
neverNothing to invoke: a listing, a server card or a skill file, not an operation.