Find ATT&CK techniques hidden in threat reports
Superlinked gives your agent one API to read threat reports and return ATT&CK suggestions with the exact source words attached.
MFA PSA, Oh My!
After sign-in, the kit sends login material and the session cookie to its server.
The threat actor can use the stolen session cookie to log in as the victim.
Your threat-intelligence agent
Read the full report against current ATT&CK definitions and labeled report spans. Keep the exact source words beside every suggestion.
Your security context
Control the ATT&CK release and the review rule.
from sie_sdk import SIEClientclient = SIEClient( api_key="sk-sie-…", base_url="https://api.superlinked.com",)result = client.extract( "modelfastino/gliner2-large-v1", {"text": "textThe threat actor is then able to use the stolen session cookie to log in as the victim where they can take multiple actions like changing the password, copying data, or pretending to be the victim"}, labels=[ "entity typethreat actor", "entity typesoftware tool", "entity typecredential", "entity typetarget system", ],)for span in result["entities"]: print(span["label"], span["text"])import { SIEClient } from '@superlinked/sie-sdk';
const client = new SIEClient('https://api.superlinked.com', {
apiKey: 'sk-sie-…',
});
const result = await client.extract(
'fastino/gliner2-large-v1',
{ text: "The threat actor is then able to use the stolen session cookie to log in as the victim where they can take multiple actions like changing the password, copying data, or pretending to be the victim" },
{ labels: ["threat actor","software tool","credential","target system"] },
);
console.log(result.entities);curl https://api.superlinked.com/v1/extract/fastino%2Fgliner2-large-v1 \
-H "Authorization: Bearer sk-sie-…" \
-H "Content-Type: application/json" \
-d "{\"items\":[{\"text\":\"The threat actor is then able to use the stolen session cookie to log in as the victim where they can take multiple actions like changing the password, copying data, or pretending to be the victim\"}],\"params\":{\"labels\":[\"threat actor\",\"software tool\",\"credential\",\"target system\"]}}"Build the "Named entities" capability into my app using the Superlinked Inference Engine (SIE).
Context
- SIE is an OpenAI-style inference API. Python SDK: `from sie_sdk import SIEClient`; TypeScript: `@superlinked/sie-sdk`.
- Base URL: https://api.superlinked.com (or my regional endpoint). Auth: Bearer key from env `SIE_API_KEY` (never hard-code it).
- Model: fastino/gliner2-large-v1 (SIE primitive: /extract). Keep the model id configurable.
Task
- Input: a block of text.
- Behaviour: return the named entities found in the text with their types
- Call the selected SIE primitive once per request and map the response into your domain type.
Deliverables
- A typed client wrapper, an application-level function for this task, error handling for timeouts/empty input, and unit tests with a stubbed client.
- Wire it into my existing stack (ask me which framework if unclear) and add a short usage example.import numpy as npfrom sie_sdk import SIEClientclient = SIEClient( api_key="sk-sie-…", base_url="https://api.superlinked.com",)query = "queryActor: threat actor
Action: use
Object: stolen session cookie
Tool: Evilginx2
Target: victim
Assertion: observed
Evidence: The threat actor is then able to use the stolen session cookie to log in as the victim where they can take multiple actions like changing the password, copying data, or pretending to be the victim"documents = [ "document 1ATT&CK technique: T1550.004 Web Session Cookie", "document 2Description: Adversaries can use stolen session cookies to authenticate to web applications and services.", "document 3ATT&CK technique: T1539 Steal Web Session Cookie", "document 4Description: An adversary may steal web application or service session cookies and use them to gain authenticated access.", "document 5ATT&CK technique: T1606.001 Web Cookies", "document 6Description: Adversaries may forge new web cookies to gain access to web applications or Internet services.", "document 7ATT&CK technique: T1185 Browser Session Hijacking", "document 8Description: Adversaries may change browser content, modify user behavior, or intercept information inside a browser session.", "document 9ATT&CK technique: T1134.001 Token Impersonation/Theft", "document 10Description: Adversaries may duplicate and impersonate another user’s existing operating-system token.",]items = [{"text": query}, *({"text": d} for d in documents)]vecs = client.encode("modelQwen/Qwen3-Embedding-8B", items)mat = np.array([v["dense"] for v in vecs])mat = mat / np.linalg.norm(mat, axis=1, keepdims=True)scores = mat[1:] @ mat[0] # cosine similarity to the queryfor i in np.argsort(scores)[::-1]: print(f"{scores[i]:.3f} {documents[i]}")import { SIEClient } from '@superlinked/sie-sdk';
const client = new SIEClient('https://api.superlinked.com', {
apiKey: 'sk-sie-…',
});
const query = "Actor: threat actor\nAction: use\nObject: stolen session cookie\nTool: Evilginx2\nTarget: victim\nAssertion: observed\nEvidence: The threat actor is then able to use the stolen session cookie to log in as the victim where they can take multiple actions like changing the password, copying data, or pretending to be the victim";
const documents = [
"ATT&CK technique: T1550.004 Web Session Cookie",
"Description: Adversaries can use stolen session cookies to authenticate to web applications and services.",
"ATT&CK technique: T1539 Steal Web Session Cookie",
"Description: An adversary may steal web application or service session cookies and use them to gain authenticated access.",
"ATT&CK technique: T1606.001 Web Cookies",
"Description: Adversaries may forge new web cookies to gain access to web applications or Internet services.",
"ATT&CK technique: T1185 Browser Session Hijacking",
"Description: Adversaries may change browser content, modify user behavior, or intercept information inside a browser session.",
"ATT&CK technique: T1134.001 Token Impersonation/Theft",
"Description: Adversaries may duplicate and impersonate another user’s existing operating-system token.",
];
const items = [{ text: query }, ...documents.map((text) => ({ text }))];
const vecs = await client.encode('Qwen/Qwen3-Embedding-8B', items);
const [q, ...d] = vecs.map((v) => v.dense);
const cosine = (a: Float32Array, b: Float32Array) => {
const dot = a.reduce((s, x, i) => s + x * b[i], 0);
return dot / (Math.hypot(...a) * Math.hypot(...b));
};
const ranked = documents
.map((doc, i) => ({ doc, score: cosine(q!, d[i]!) }))
.sort((a, b) => b.score - a.score);
console.log(ranked);# Encode the query + candidates in one batch, then rank by cosine.
curl https://api.superlinked.com/v1/encode/Qwen%2FQwen3-Embedding-8B \
-H "Authorization: Bearer sk-sie-…" \
-H "Content-Type: application/json" \
-d "{\"items\":[{\"text\":\"Actor: threat actor\\nAction: use\\nObject: stolen session cookie\\nTool: Evilginx2\\nTarget: victim\\nAssertion: observed\\nEvidence: The threat actor is then able to use the stolen session cookie to log in as the victim where they can take multiple actions like changing the password, copying data, or pretending to be the victim\"},{\"text\":\"ATT&CK technique: T1550.004 Web Session Cookie\"},{\"text\":\"Description: Adversaries can use stolen session cookies to authenticate to web applications and services.\"},{\"text\":\"ATT&CK technique: T1539 Steal Web Session Cookie\"},{\"text\":\"Description: An adversary may steal web application or service session cookies and use them to gain authenticated access.\"},{\"text\":\"ATT&CK technique: T1606.001 Web Cookies\"},{\"text\":\"Description: Adversaries may forge new web cookies to gain access to web applications or Internet services.\"},{\"text\":\"ATT&CK technique: T1185 Browser Session Hijacking\"},{\"text\":\"Description: Adversaries may change browser content, modify user behavior, or intercept information inside a browser session.\"},{\"text\":\"ATT&CK technique: T1134.001 Token Impersonation/Theft\"},{\"text\":\"Description: Adversaries may duplicate and impersonate another user’s existing operating-system token.\"}],\"params\":{\"output_types\":[\"dense\"]}}"Build the "Search" capability into my app using the Superlinked Inference Engine (SIE).
Context
- SIE is an OpenAI-style inference API. Python SDK: `from sie_sdk import SIEClient`; TypeScript: `@superlinked/sie-sdk`.
- Base URL: https://api.superlinked.com (or my regional endpoint). Auth: Bearer key from env `SIE_API_KEY` (never hard-code it).
- Model: Qwen/Qwen3-Embedding-8B (SIE primitive: /encode). Keep the model id configurable.
Task
- Input: a query string plus a list of candidate documents.
- Behaviour: return the candidates ranked by semantic similarity to the query, with a score per candidate
- Encode the query and candidates in one batched /encode call, then rank by cosine similarity in the client. Do not call the API per candidate.
Deliverables
- A typed client wrapper, an application-level function for this task, error handling for timeouts/empty input, and unit tests with a stubbed client.
- Wire it into my existing stack (ask me which framework if unclear) and add a short usage example.from sie_sdk import SIEClientclient = SIEClient( api_key="sk-sie-…", base_url="https://api.superlinked.com",)query = "queryObserved adversary behavior: The threat actor is then able to use the stolen session cookie to log in as the victim where they can take multiple actions like changing the password, copying data, or pretending to be the victim"documents = [ "document 1ATT&CK technique: T1550.004 Web Session Cookie", "document 2Description: Adversaries can use stolen session cookies to authenticate to web applications and services.", "document 3ATT&CK technique: T1539 Steal Web Session Cookie", "document 4Description: An adversary may steal web application or service session cookies and use them to gain authenticated access.", "document 5ATT&CK technique: T1606.001 Web Cookies", "document 6Description: Adversaries may forge new web cookies to gain access to web applications or Internet services.", "document 7ATT&CK technique: T1185 Browser Session Hijacking", "document 8Description: Adversaries may change browser content, modify user behavior, or intercept information inside a browser session.", "document 9ATT&CK technique: T1134.001 Token Impersonation/Theft", "document 10Description: Adversaries may duplicate and impersonate another user’s existing operating-system token.",]items = [{"id": str(i), "text": d} for i, d in enumerate(documents)]ranked = client.score("modelQwen/Qwen3-Reranker-4B", {"text": query}, items)for r in ranked["scores"]: print(r["score"], documents[int(r["item_id"])])import { SIEClient } from '@superlinked/sie-sdk';
const client = new SIEClient('https://api.superlinked.com', {
apiKey: 'sk-sie-…',
});
const query = "Observed adversary behavior: The threat actor is then able to use the stolen session cookie to log in as the victim where they can take multiple actions like changing the password, copying data, or pretending to be the victim";
const documents = [
"ATT&CK technique: T1550.004 Web Session Cookie",
"Description: Adversaries can use stolen session cookies to authenticate to web applications and services.",
"ATT&CK technique: T1539 Steal Web Session Cookie",
"Description: An adversary may steal web application or service session cookies and use them to gain authenticated access.",
"ATT&CK technique: T1606.001 Web Cookies",
"Description: Adversaries may forge new web cookies to gain access to web applications or Internet services.",
"ATT&CK technique: T1185 Browser Session Hijacking",
"Description: Adversaries may change browser content, modify user behavior, or intercept information inside a browser session.",
"ATT&CK technique: T1134.001 Token Impersonation/Theft",
"Description: Adversaries may duplicate and impersonate another user’s existing operating-system token.",
];
const items = documents.map((text, i) => ({ id: String(i), text }));
const ranked = await client.score('Qwen/Qwen3-Reranker-4B', { text: query }, items);
console.log(ranked.scores.map(({ itemId, score }) => ({ document: documents[Number(itemId)], score })));curl https://api.superlinked.com/v1/score/Qwen%2FQwen3-Reranker-4B \
-H "Authorization: Bearer sk-sie-…" \
-H "Content-Type: application/json" \
-d "{\"query\":{\"text\":\"Observed adversary behavior: The threat actor is then able to use the stolen session cookie to log in as the victim where they can take multiple actions like changing the password, copying data, or pretending to be the victim\"},\"items\":[{\"id\":\"0\",\"text\":\"ATT&CK technique: T1550.004 Web Session Cookie\"},{\"id\":\"1\",\"text\":\"Description: Adversaries can use stolen session cookies to authenticate to web applications and services.\"},{\"id\":\"2\",\"text\":\"ATT&CK technique: T1539 Steal Web Session Cookie\"},{\"id\":\"3\",\"text\":\"Description: An adversary may steal web application or service session cookies and use them to gain authenticated access.\"},{\"id\":\"4\",\"text\":\"ATT&CK technique: T1606.001 Web Cookies\"},{\"id\":\"5\",\"text\":\"Description: Adversaries may forge new web cookies to gain access to web applications or Internet services.\"},{\"id\":\"6\",\"text\":\"ATT&CK technique: T1185 Browser Session Hijacking\"},{\"id\":\"7\",\"text\":\"Description: Adversaries may change browser content, modify user behavior, or intercept information inside a browser session.\"},{\"id\":\"8\",\"text\":\"ATT&CK technique: T1134.001 Token Impersonation/Theft\"},{\"id\":\"9\",\"text\":\"Description: Adversaries may duplicate and impersonate another user’s existing operating-system token.\"}]}"Build the "Rerank" capability into my app using the Superlinked Inference Engine (SIE).
Context
- SIE is an OpenAI-style inference API. Python SDK: `from sie_sdk import SIEClient`; TypeScript: `@superlinked/sie-sdk`.
- Base URL: https://api.superlinked.com (or my regional endpoint). Auth: Bearer key from env `SIE_API_KEY` (never hard-code it).
- Model: Qwen/Qwen3-Reranker-4B (SIE primitive: /score). Keep the model id configurable.
Task
- Input: a query string plus a list of candidate documents.
- Behaviour: reorder the candidates by true relevance to the query using the cross-encoder
- Call the selected SIE primitive once per request and map the response into your domain type.
Deliverables
- A typed client wrapper, an application-level function for this task, error handling for timeouts/empty input, and unit tests with a stubbed client.
- Wire it into my existing stack (ask me which framework if unclear) and add a short usage example.from sie_sdk import SIEClientclient = SIEClient( api_key="API keysk-sie-…", base_url="https://api.superlinked.com",)messages = [ {"role": "user", "content": "textSelect the ATT&CK candidate that directly describes this behavior. Keep the evidence quote exact.
Behavior: Threat actor uses stolen session cookie to log in as victim and perform actions
Source quote: The threat actor is then able to use the stolen session cookie to log in as the victim where they can take multiple actions like changing the password, copying data, or pretending to be the victim
Candidates: T1539 Steal Web Session Cookie; T1550.004 Web Session Cookie; T1185 Browser Session Hijacking; T1606.001 Web Cookies; T1134.001 Token Impersonation/Theft."},]result = client.chat_completions( "modelQwen/Qwen3.6-27B:no-spec", messages, max_completion_tokens=max tokens256,)print(result["choices"][0]["message"]["content"])import { SIEClient } from '@superlinked/sie-sdk';
const client = new SIEClient('https://api.superlinked.com', {
apiKey: 'sk-sie-…',
});
const result = await client.chatCompletions({
model: 'Qwen/Qwen3.6-27B:no-spec',
messages: [
{ role: 'user', content: "Select the ATT&CK candidate that directly describes this behavior. Keep the evidence quote exact.\n\nBehavior: Threat actor uses stolen session cookie to log in as victim and perform actions\nSource quote: The threat actor is then able to use the stolen session cookie to log in as the victim where they can take multiple actions like changing the password, copying data, or pretending to be the victim\nCandidates: T1539 Steal Web Session Cookie; T1550.004 Web Session Cookie; T1185 Browser Session Hijacking; T1606.001 Web Cookies; T1134.001 Token Impersonation/Theft." },
],
max_completion_tokens: 256,
});
console.log(result.choices[0]?.message.content);curl https://api.superlinked.com/v1/chat/completions \
-H "Authorization: Bearer sk-sie-…" \
-H "Content-Type: application/json" \
-d "{\"model\":\"Qwen/Qwen3.6-27B:no-spec\",\"messages\":[{\"role\":\"user\",\"content\":\"Select the ATT&CK candidate that directly describes this behavior. Keep the evidence quote exact.\\n\\nBehavior: Threat actor uses stolen session cookie to log in as victim and perform actions\\nSource quote: The threat actor is then able to use the stolen session cookie to log in as the victim where they can take multiple actions like changing the password, copying data, or pretending to be the victim\\nCandidates: T1539 Steal Web Session Cookie; T1550.004 Web Session Cookie; T1185 Browser Session Hijacking; T1606.001 Web Cookies; T1134.001 Token Impersonation/Theft.\"}],\"max_completion_tokens\":256}"Build the "Chat" capability into my app using the Superlinked Inference Engine (SIE).
Context
- SIE is an OpenAI-style inference API. Python SDK: `from sie_sdk import SIEClient`; TypeScript: `@superlinked/sie-sdk`.
- Base URL: https://api.superlinked.com (or my regional endpoint). Auth: Bearer key from env `SIE_API_KEY` (never hard-code it).
- Model: Qwen/Qwen3.6-27B:no-spec (OpenAI-compatible endpoint: /v1/chat/completions). Keep the model id configurable.
Task
- Input: a block of text.
- Behaviour: return the model’s answer to the prompt
- Send one POST /v1/chat/completions request (SDK: chat_completions / chatCompletions) with an optional system message for instructions, the user's text as the user message, and max_completion_tokens. Read the answer from choices[0].message.content.
Deliverables
- A typed client wrapper, an application-level function for this task, error handling for timeouts/empty input, and unit tests with a stubbed client.
- Wire it into my existing stack (ask me which framework if unclear) and add a short usage example.The threat actor is then able to use the stolen session cookiecredential to log in as the victim where they can take multiple actions like changing the passwordcredential, copying data, or pretending to be the victim
Compare models for this task
The agent separates cookie reuse from cookie theft
View on GitHubDeploy your way
Managed Cloud
Full compute toolkit for your agents with zero ops.
- No idle GPUs, pay for what you use
- Fits your stack: SDK, API, CLI, MCP
- Zero lock-in, self-host the same stack
- SOC 2 Type 2, US or EU data residency
no credit card required
Self-host with K8s
Easy & scalable deployment in your own cloud.
- Terraform to your cloud in minutes
- Apache-2.0, same engine as Cloud
- Scales to zero, no bill between jobs
- Per-tenant pools, no noisy neighbors
Deploy SIE to our AWS account with the superlinked/sie/aws Terraform module. Docs: superlinked.com/docs/deploymentDeploy SIE to our GCP project with the superlinked/sie/google Terraform module. Docs: superlinked.com/docs/deploymentDeploy SIE to our Azure AKS cluster via helm install. Requirements: superlinked.com/docs/deployment Run locally
Run the same models on your own machine.
- Runs on NVIDIA GPU or Apple Silicon
- One command, no Docker or cluster
- All 100+ Cloud models, fully offline
- Same SDK and IDs, no code changes
pip install "sie-server[local]" && sie-server servepip install "sie-server[local]" && sie-server serve --device cuda