Home · Business · IT, Data & Security · Helpdesk & devices

PARTLY

As of 13 August 2026, AI can only partly remove malware from your PC.

This still needs a person who signs their name to it.

Can you do it?

5 minutesto a draft.

1 hourto something you’d act on.

Cost, all in£0

Skill neededchat-fluent

Who has to check ita professional

What the alternative costsNo comparable alternative price is provided in the available tool data.

If this goes wrong, you can delete useful evidence, spread the infection across a workplace network or leave an attacker with access to company data.

What to actually do

  1. Hand it to a person

    The route this page recommends

    Someone with a licence or accountable authority has to sign this before it counts.

  2. Use a tool built for this

    Second choice

  3. Do it yourself

    The distant third

    A chat interface, chat-fluent skill, and roughly 1 hour until you can act on the result.

    How to actually do it

    1. Open your organisation's IT or security incident channel and note whether the PC is company-managed, connected to a work network, or used to access company accounts.
    2. If there are signs of ransomware, credential theft, unauthorised access or active spread, stop using the PC and follow your organisation's incident procedure instead of trying to clean it yourself.
    3. Gather the Windows version, the symptoms, their start time, recent downloads or software changes, the affected account, and any exact alerts shown by Windows Security or your approved endpoint protection.
    4. Paste those facts into the prompt, excluding passwords, recovery codes, personal documents and any confidential data that your organisation does not allow in an AI service.
    5. Run only the scans and isolation actions approved by your organisation, following the AI's instructions and recording the tool name, scan type, time and exact result.
    6. Compare the proposed actions against your organisation's IT guidance, then send the generated incident summary and scan results to your IT or security team before deleting files or changing system settings.
    7. After IT confirms the remediation plan, apply their instructions, change credentials from a known-clean device if they direct you to do so, and obtain confirmation before reconnecting the PC to workplace systems.

    Prompt

    Act as a cautious UK workplace IT support assistant. Help me respond to a possible malware infection on a Windows PC without guessing and without giving destructive commands. First ask only for the facts you need: Windows version, whether the PC is company-managed, symptoms, when they began, recent downloads or software changes, whether the PC is connected to a work network, and the exact results from trusted security tools. Tell me what to do immediately to reduce risk, including when to disconnect from networks and when to stop using the PC. Give me a step-by-step plan using built-in Windows security features or reputable tools already approved by my organisation. Do not tell me to delete suspicious files manually, edit the registry, disable security controls or run a command unless you explain the risk and give a safer alternative. Separate actions I can take from actions that require my IT team. For each step, state what result to expect and what evidence to record. If the symptoms suggest credential theft, ransomware, unauthorised access or a continuing workplace incident, tell me to contact my organisation's IT or security team immediately rather than continuing. Do not claim the PC is clean unless a trusted scan and my IT team support that conclusion. At the end, give me a short incident summary I can send to IT. Use British English.

    Open it prefilled in ChatGPT or Claude, or copy it into Gemini, which takes no prefill link.

What it gets wrong

  • AI cannot inspect the PC, its running processes, endpoint alerts or network connections unless an authorised security tool supplies that evidence.
  • AI cannot reliably prove that malware has been removed or that an attacker no longer has access.
  • AI cannot decide whether deleting a suspicious file will destroy evidence needed for an internal investigation.
  • AI cannot take responsibility for isolating a workplace device, notifying affected people or meeting your organisation's incident process.
  • AI cannot safely replace an IT or security professional when ransomware, stolen credentials or unauthorised access is possible.

What caps this at PARTLY: stakes of error, verification cost and private data access.

How we scored this

Five axes, each scored nought to two by hand: ten means AI carries the task cleanly, and the thresholds that turn a total into YES, PARTLY or NO are published in the methodology. Each axis name links to its definition.

AxisScore (0–2)
Output2
Inputs1
Verification1
Liability1
Effort delta1
Total6 / 10

The methodology and its thresholds are published in full.

FAQ

Can ChatGPT remove malware from my PC?
It can guide you through safer checks and help interpret scan results, but it cannot inspect or clean the PC by itself. For a work device, use your organisation's IT or security process, especially if ransomware, stolen credentials or unauthorised access is possible.
Is it safe to use AI for malware removal?
It is reasonably safe for gathering symptoms, explaining approved security-tool results and preparing an incident report. Do not paste passwords or confidential files, run unexplained commands, delete suspicious files manually or treat an AI response as proof that the PC is clean.
Should I disconnect my computer from the internet if it has malware?
Possibly, but follow your organisation's incident procedure because isolation can affect evidence and remote investigation. If you suspect ransomware, credential theft or active spread, stop using the PC and contact your IT or security team immediately.
How do I know if malware has been removed?
A clean scan is useful evidence, but it does not by itself prove that the machine or affected accounts are safe. Ask your organisation's IT or security team to confirm the remediation, account checks and conditions for reconnecting the PC.

Nearby answers

All Helpdesk & devices rulings

Assessed by gpt-5.6-luna (gpt-5.6-luna) on 2026-08-13, second-checked by an independent model. Wrong somewhere? Email [email protected] and it gets re-checked.

The newsletter

AI news, new answers and product picks, straight to your inbox.