erukude/ vulnerability-researcher

2,003 Downloads Updated 1 week ago

A fine-tuned Qwen 3.5 35B model for vulnerability finding review, false-positive reduction, and JSON-only security triage.

vision tools thinking 35b

ollama run erukude/vulnerability-researcher:35b

curl http://localhost:11434/api/chat \
  -d '{
    "model": "erukude/vulnerability-researcher:35b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='erukude/vulnerability-researcher:35b',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'erukude/vulnerability-researcher:35b',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Applications

Claude Code

Claude Code ollama launch claude --model erukude/vulnerability-researcher:35b

OpenCode

OpenCode ollama launch opencode --model erukude/vulnerability-researcher:35b

Hermes Agent

Hermes Agent ollama launch hermes --model erukude/vulnerability-researcher:35b

OpenClaw

OpenClaw ollama launch openclaw --model erukude/vulnerability-researcher:35b

Models

Name

1 model

Size / Usage

Context

Input

vulnerability-researcher:35b

24GB · 256K context window · Text, Image · 1 week ago

vulnerability-researcher:35b

24GB

256K

Text, Image

Readme

vulnerability-researcher

erukude/vulnerability-researcher:35b is a fine-tuned Qwen 3.5 35B model for conservative vulnerability finding review.

Summary

An expert vulnerability researcher model fine-tuned with a LoRA adapter to separate obvious non-issues from findings that need deeper review. It is evidence-driven, cautious by default, and returns valid JSON only.

Best For

Vulnerability finding triage
False-positive reduction
Exploitability sanity checks
Source-to-sink review
Security review automation

Verdicts

dismissed - clearly safe, with specific code evidence
inconclusive - possible issue, but evidence is incomplete
validated - obvious textbook vulnerability with attacker control, reachability, dangerous sink, no guard, and plausible impact

Run

ollama run erukude/vulnerability-researcher:35b

Example Prompt

Review this finding.

Package: example-lib
Version: 1.2.3
Finding: ...
Source: ...
Sink: ...
Reachability: ...
Guards: ...
Impact: ...
Code evidence: ...

Output

Returns JSON:

{
  "verdict": "inconclusive",
  "reason": "One to three concise sentences explaining the decision.",
  "code_evidence": [
    "Specific code fact used for the decision."
  ],
  "evidence_gaps": [
    "Missing fact needed to make a stronger decision."
  ],
  "needs_human_review": true
}

Model Details

Base: qwen3.5:35b
Fine-tune: LoRA adapter
Temperature: 0.2
Top-p: 0.95
Top-k: 20
Output: valid JSON only
License: Apache License 2.0

Developer

Created and maintained by Sai Teja Erukude.

Note

Built for defensive security research and responsible vulnerability review. When evidence is weak or ambiguous, the model is designed to return inconclusive.

# vulnerability-researcher

`erukude/vulnerability-researcher:35b` is a fine-tuned Qwen 3.5 35B model for conservative vulnerability finding review.

## Summary

An expert vulnerability researcher model fine-tuned with a LoRA adapter to separate obvious non-issues from findings that need deeper review. It is evidence-driven, cautious by default, and returns valid JSON only.

## Best For

- Vulnerability finding triage
- False-positive reduction
- Exploitability sanity checks
- Source-to-sink review
- Security review automation

## Verdicts

- `dismissed` - clearly safe, with specific code evidence
- `inconclusive` - possible issue, but evidence is incomplete
- `validated` - obvious textbook vulnerability with attacker control, reachability, dangerous sink, no guard, and plausible impact

## Run

```powershell
ollama run erukude/vulnerability-researcher:35b
```

## Example Prompt

```text
Review this finding.

Package: example-lib
Version: 1.2.3
Finding: ...
Source: ...
Sink: ...
Reachability: ...
Guards: ...
Impact: ...
Code evidence: ...
```

## Output

Returns JSON:

```json
{
  "verdict": "inconclusive",
  "reason": "One to three concise sentences explaining the decision.",
  "code_evidence": [
    "Specific code fact used for the decision."
  ],
  "evidence_gaps": [
    "Missing fact needed to make a stronger decision."
  ],
  "needs_human_review": true
}
```

## Model Details

- Base: `qwen3.5:35b`
- Fine-tune: LoRA adapter
- Temperature: `0.2`
- Top-p: `0.95`
- Top-k: `20`
- Output: valid JSON only
- License: Apache License 2.0

## Developer

Created and maintained by **Sai Teja Erukude**.

## Note

Built for defensive security research and responsible vulnerability review. When evidence is weak or ambiguous, the model is designed to return `inconclusive`.

Paste, drop or click to upload images (.png, .jpeg, .jpg, .svg, .gif)