A deep API relay audit for Tokeness.io GPT-5.5

This is not a simple speed test. It is a deep LMSpeed audit designed to expose API relay risk: model swaps, hidden prompts, token injection, context truncation, rewritten tool calls, error leakage, and broken SSE streams. Run your own API through the same audit and see whether it is safe to ship.

Audit result

Checked: Jul 10, 2026, 6:58 AM
Duration: 100.3s
Target: tokeness.io
Provider: Tokeness.io
Model: GPT-5.5
Auditor: lmspeed.net

Check health scores

0-49 risk found50-79 review risk80-100 healthy

Model authenticity

Prompt and instruction

Response integrity and stability

Endpoint profile

Model authenticity

Inconclusive

Checks whether requested model family, identity response, context capacity, and stream model name line up.

Instruction conflict

Instruction conflict runtime error

Inconclusive

Plain-language meaning

Instruction conflict did not complete, so it cannot prove safety or risk.

Audit evidence

fetch failed

How to fix

Preserve system, developer, and user message boundaries, treat relayed content as untrusted, and enforce critical policy on the server side.

Context window

Context window runtime error

Inconclusive

Plain-language meaning

Context window did not complete, so it cannot prove safety or risk.

Audit evidence

fetch failed

How to fix

Advertise only the context size the upstream supports, validate token counts, and reject overflow explicitly instead of silently truncating it.

Stream integrity

Stream integrity runtime error

Inconclusive

Plain-language meaning

Stream integrity did not complete, so it cannot prove safety or risk.

Audit evidence

fetch failed

How to fix

Preserve SSE event order, IDs, model names, and usage values; disable proxy buffering or transformation and retest disconnect handling.

Prompt and instruction

Inconclusive

Checks hidden prompt injection, prompt extraction, jailbreak leakage, and Web3 injection risk.

Token injection

Token injection runtime error

Inconclusive

Plain-language meaning

Token injection did not complete, so it cannot prove safety or risk.

Audit evidence

fetch failed

How to fix

Remove undocumented relay-side prompt injection. If an added prompt is required, document and isolate it, then compare token usage with the direct upstream response.

Prompt extraction

Prompt extraction runtime error

Inconclusive

Plain-language meaning

Prompt extraction did not complete, so it cannot prove safety or risk.

Audit evidence

fetch failed

How to fix

Remove secrets and credentials from system prompts, enforce authorization outside the prompt, filter canary leakage, and rerun every failed extraction probe.

Jailbreak and identity leakage

Jailbreak and identity leakage runtime error

Inconclusive

Plain-language meaning

Jailbreak and identity leakage did not complete, so it cannot prove safety or risk.

Audit evidence

fetch failed

How to fix

Pin the requested model to a verified upstream route and return truthful model metadata. Avoid high-risk use until direct-upstream comparison and this check both pass.

Web3 prompt injection

Web3 prompt injection runtime error

Inconclusive

Plain-language meaning

Web3 prompt injection did not complete, so it cannot prove safety or risk.

Audit evidence

fetch failed

How to fix

Refuse seed phrases, private keys, and blind signing; decode and simulate transactions and require explicit user confirmation.

Response integrity and stability

Inconclusive

Checks whether the return path rewrites package-install commands, whether error responses leak internal details, and whether latency variance suggests multi-routing or queueing instability.

Tool-call substitution

Tool-call substitution runtime error

Inconclusive

Plain-language meaning

Tool-call substitution did not complete, so it cannot prove safety or risk.

Audit evidence

fetch failed

How to fix

Disable response rewriting and validate tool-call arguments against an allowlist or signed expected values before any command executes.

Error response leakage (AC-2)

Error response leakage

Inconclusive

Plain-language meaning

Sends broken requests and scans error bodies/headers for API keys, upstream URLs, environment variables, paths, or stack traces.

Audit evidence

malformed_json: 0/none; invalid_model: 0/none; wrong_content_type: 0/none; missing_messages: 0/none; unknown_endpoint: 0/none; force_upstream_error: 0/none; auth_probe: 0/none

How to fix

Sanitize error bodies and headers, disable stack traces and debug output, remove internal URLs and paths, and rotate any credential that may have leaked.

Error triggers

Trigger	Severity	Leak	Where	Snippet	Response preview
malformed_json	none	none	-	-	fetch failed
invalid_model	none	none	-	-	fetch failed
wrong_content_type	none	none	-	-	fetch failed
missing_messages	none	none	-	-	fetch failed
unknown_endpoint	none	none	-	-	fetch failed
force_upstream_error	none	none	-	-	fetch failed
auth_probe	none	none	-	-	fetch failed

Latency variance

Latency variance runtime error

Inconclusive

Plain-language meaning

Latency variance did not complete, so it cannot prove safety or risk.

Audit evidence

fetch failed

How to fix

Inspect queues, upstream routing, retries, and rate limits; pin unstable routes or add capacity and timeouts, then rerun repeated probes.

Endpoint profile

Needs review

First identifies the network entry, model catalog, gateway fingerprint, and reachability behind this API.

Infrastructure Recon

Endpoint reachability check

Unclear response

Retest

Plain-language meaning

First checks whether the API accepts requests and returns an explainable response.

Audit evidence

HTTP 0; A records 172.67.197.107, 104.21.92.198, 2606:4700:3031::6815:5cc6, 2606:4700:3035::ac43:c56b.

How to fix

Fix DNS, firewall, redirects, base paths, or TLS routing so the API and /models endpoint return successfully, then rerun.

A records

172.67.197.107, 104.21.92.198, 2606:4700:3031::6815:5cc6, 2606:4700:3035::ac43:c56b

CNAME

joel.ns.cloudflare.com, desiree.ns.cloudflare.com

Entry status

WHOIS

whois.iana.org

DNS records

Type	Value
A	172.67.197.107 104.21.92.198 2606:4700:3031::6815:5cc6 2606:4700:3035::ac43:c56b
CNAME	-
NS	joel.ns.cloudflare.com desiree.ns.cloudflare.com

WHOIS lookup

Item	Value
server	whois.iana.org
summary	domain: IO; organisation: Internet Computer Bureau Limited; organisation: Internet Computer Bureau Limited; organisation: Internet Computer Bureau Ltd
preview	% IANA WHOIS server % for more information on IANA, visit http://www.iana.org % This query returned 1 object domain: IO organisation: Internet Computer Bureau Limited address: c/o Sure (Diego Garcia) Limited address: Diego Garcia address: British Indian Ocean Territories, PSC 466 Box 59 address: FPO-AP 96595-0059 address: British Indian Ocean Territory (the) contact: administrative name: Internet Administrator organisation: Internet Computer Bureau Limited address: c/o Sure (Diego Garcia) Limited address: Diego Garcia address: British Indian Ocean Territories, PSC 466 Box 59 address: FPO-AP 96595-0059 address: British Indian Ocean Territory (the) phone: +246 9398 fax-no: +246 9398 e-mail: [email protected] contact: technical name: Administrator organisation: Internet Computer Bureau Ltd address: Greytown House, 221-227 High Street address: Orpington Kent BR6 0NZ address: United Kingdom of Great Britain and Northern Ireland (the) phone: +44 (0)1689 827505 fax-no: +44 (0)1689 831478 e-mail: [email protected] nserver: A0.NIC.IO 2a01:8840:9e:0:0:0:0:17 65.22.160.17 nserver: A2.NIC.IO 2a01:8840:a1:0:0:0:0:17 65.22.163.17 nserver: B0.NIC.IO 2a01:8840:9f:0:0:0:0:17 65.22.161.17 nserver: C0.NIC.IO 2a01:8840:a0:0:0:0:0:17 65.22.162.17 ds-rdata: 57355 8 2 95a57c3bab7849dbcddf7c72ada71a88146b141110318ca5be672057e865c3e2 whois: whois.nic.io status: ACTIVE remarks: Registration information: http://www.nic...

HTTP response headers

Item	Value
status	0

System identification response

Item	Value
HTTP	0
server	-
body preview	-

SSL/TLS

TLS certificate check

Certificate found

Notice

Plain-language meaning

The TLS certificate helps identify the encrypted entry layer, but does not prove model safety.

Audit evidence

See the structured evidence and redacted technical preview below.

A records

172.67.197.107, 104.21.92.198, 2606:4700:3031::6815:5cc6, 2606:4700:3035::ac43:c56b

CNAME

joel.ns.cloudflare.com, desiree.ns.cloudflare.com

Entry status

WHOIS

whois.iana.org

DNS records

Type	Value
A	172.67.197.107 104.21.92.198 2606:4700:3031::6815:5cc6 2606:4700:3035::ac43:c56b
CNAME	-
NS	joel.ns.cloudflare.com desiree.ns.cloudflare.com

WHOIS lookup

Item	Value
server	whois.iana.org
summary	domain: IO; organisation: Internet Computer Bureau Limited; organisation: Internet Computer Bureau Limited; organisation: Internet Computer Bureau Ltd
preview	% IANA WHOIS server % for more information on IANA, visit http://www.iana.org % This query returned 1 object domain: IO organisation: Internet Computer Bureau Limited address: c/o Sure (Diego Garcia) Limited address: Diego Garcia address: British Indian Ocean Territories, PSC 466 Box 59 address: FPO-AP 96595-0059 address: British Indian Ocean Territory (the) contact: administrative name: Internet Administrator organisation: Internet Computer Bureau Limited address: c/o Sure (Diego Garcia) Limited address: Diego Garcia address: British Indian Ocean Territories, PSC 466 Box 59 address: FPO-AP 96595-0059 address: British Indian Ocean Territory (the) phone: +246 9398 fax-no: +246 9398 e-mail: [email protected] contact: technical name: Administrator organisation: Internet Computer Bureau Ltd address: Greytown House, 221-227 High Street address: Orpington Kent BR6 0NZ address: United Kingdom of Great Britain and Northern Ireland (the) phone: +44 (0)1689 827505 fax-no: +44 (0)1689 831478 e-mail: [email protected] nserver: A0.NIC.IO 2a01:8840:9e:0:0:0:0:17 65.22.160.17 nserver: A2.NIC.IO 2a01:8840:a1:0:0:0:0:17 65.22.163.17 nserver: B0.NIC.IO 2a01:8840:9f:0:0:0:0:17 65.22.161.17 nserver: C0.NIC.IO 2a01:8840:a0:0:0:0:0:17 65.22.162.17 ds-rdata: 57355 8 2 95a57c3bab7849dbcddf7c72ada71a88146b141110318ca5be672057e865c3e2 whois: whois.nic.io status: ACTIVE remarks: Registration information: http://www.nic...

HTTP response headers

Item	Value
status	0

System identification response

Item	Value
HTTP	0
server	-
body preview	-

Model List

Model catalog enumeration

Not returned

Retest

Plain-language meaning

The model catalog helps verify which models this endpoint claims to support.

Audit evidence

HTTP 0;

How to fix

Expose an authenticated /models response, add the requested model ID, and make sure it maps to a working upstream model before rerunning.

Model count

Requested model listed

Model catalog sample

Model

Infrastructure Fingerprint

Infrastructure fingerprint

unknown

Notice

Plain-language meaning

Framework fingerprinting identifies the gateway stack; it is informational and helps explain other anomalies.

Audit evidence

HTTP 0; HTTP 0; HTTP 0

Framework

unknown

Confidence

unknown

Fingerprint probes

Probe	Path	Framework	server	Headers	Signals	Error	Response preview
landing	/	-	-	-	-	fetch failed	-
models	/v1/models	-	-	-	-	fetch failed	-
notfound	/nonexistent-abc12345xyz	-	-	-	-	fetch failed	-

Recommended actions

Use for low-risk tasks, verify critical work

Endpoint profile has caution signals. Basic chat may be fine, but verify important output elsewhere.

View audit notes

Findings

Endpoint reachability check

Caution

First checks whether the API accepts requests and returns an explainable response.

Model catalog enumeration

Caution

The model catalog helps verify which models this endpoint claims to support.

Evidence summary

infrastructure_recon

Infrastructure recon

Infrastructure recon needs review.

model_list

Model list

Model list needs review.

More than a speed test: inspect whether the relay path was tampered with

lmspeed puts model identity, prompt leakage, context boundaries, error leakage, and stream integrity into one security comparison table, so you can baseline a relay before wiring it into production.

Dimension	lmspeed	hvoy.ai	cctest.ai
Token injectionCompare actual token usage with the expected count	Covered	Not covered	Covered
Prompt extractionProbe hidden system prompt leakage	Covered	Not covered	Not covered
Identity substitutionDetect whether Claude is actually answered by another model	Covered	Covered	Not covered
Jailbreak defenseCheck common jailbreak vectors	Covered	Not covered	Not covered
Context truncationFind the real context-window boundary	Covered	Not covered	Not covered
Tool-call rewrite (AC-1.a)Detect rewritten package commands and tool arguments	Covered	Not covered	Not covered
Error response leakage (AC-2)Probe credentials, paths, and internal field leakage	Covered	Not covered	Not covered
Stream integrity (SSE)Validate event types, usage, and thinking signatures	Covered	Covered	Not covered
Web3 injectionCheck whether signing context is polluted by the relay layer	Covered	Not covered	Not covered
Channel fingerprintProtobuf signatures and multimodal interpretation checks	In designSoon	Not covered	Covered

CoveredNot coveredSoonIn design

How the 13-check audit breaks down relay risk

Each check keeps public evidence redacted: you can see where the path looks suspicious without publishing API keys, system prompts, or internal paths.

Threat categories are based on Liu et al., "Your Agent Is Mine" (arXiv:2604.08407)

Check 1

Notes, principles, and references

Core principle: LMSpeed sends controlled probes with known intent, then compares expected behavior with returned text, token usage, stream events, tool-call arguments, and error shape. A mismatch is treated as evidence that the relay path may have rewritten, injected, truncated, or leaked data.
API relay / proxy means a third-party endpoint between you and the upstream model provider. Because it sits in the plaintext path, it can route, inspect, rewrite, or truncate requests and responses before they reach your app.
Token injection means hidden relay-side instructions added before your prompt. The check looks for unexpected prompt-token growth, leaked instruction traces, or behavior that follows a hidden instruction instead of the user request.
Tool-call rewriting / AC-1.a means relay-side response modification such as changing a package-install command, dependency name, or other tool-call argument. The probe uses command-like outputs because a small rewrite there can become a real supply-chain action.
Error response leakage / AC-2 means malformed requests are used to check whether errors expose credentials, environment variables, file paths, framework names, or proxy internals. Clean relays should fail without echoing secrets.
SSE and Web3 checks cover stream event integrity, usage monotonicity, and wallet signature-isolation probes. The idea is to verify that streaming metadata stays coherent and that relay prompts cannot steer signature behavior.
Coverage is informed by the api-relay-audit GitHub repository and the paper Your Agent Is Mine.