₦airaland Forum

Nigeria’s National Information Technology Development Agency has issued a fresh cybersecurity advisory warning that newly discovered vulnerabilities in OpenAI’s latest large language models could expose users to serious data-leakage risks.

In a notice released through its official X account on Sunday, NITDA’s Computer Emergency Readiness and Response Team (CERRT.NG) disclosed that seven vulnerabilities were identified in OpenAI’s GPT-4.0 and GPT-5 series models, enabling attackers to manipulate ChatGPT through indirect prompt injections hidden in seemingly harmless online content.

According to the advisory, attackers can plant malicious instructions inside “webpages, comments, or crafted URLs,” making it possible for ChatGPT to execute unintended commands during normal browsing, summarisation, or search activities.

CERRT further notes that some of the flaws allow threat actors to bypass safety systems using trusted domains or exploit markdown rendering weaknesses to hide harmful input.

One of the more concerning issues is the potential for long-term manipulation. The agency warns that attackers could even “poison ChatGPT’s memory so that injected instructions persist across future interactions,” raising alarms for both individual users and enterprise systems.

While OpenAI has reportedly implemented partial fixes, CERRT maintains that large language models still face fundamental challenges in distinguishing legitimate user intent from maliciously embedded data.

Potential Impact
NITDA warns that the vulnerabilities could lead to unauthorized actions, information leakage, manipulated outputs, and long-term behavioral influence.

Crucially, users may be affected without any direct interaction: the advisory states that attacks can trigger “without clicking anything,” especially when ChatGPT processes search results or webpages containing concealed payloads.

Recommended Preventive Measures
CERRT advises organisations and users to adopt immediate safeguards, including:

Limiting or disabling ChatGPT’s browsing and summarisation features for untrusted websites.

Enabling capabilities like browsing or memory only when necessary.

Regularly updating GPT-4.0 and GPT-5 models to ensure known vulnerabilities are patched.

NITDA alerts Nigerians on GPT flaws
The National Information Technology Development Agency on Monday, warned Nigerians on the existence of new vulnerabilities in OpenAI’s GPT-4.0 and GPT-5 series which could expose users to data-leakage.

The advisory was issued by the agency’s Director of Corporate Affairs and External Relations, Mrs Hadiza Umar, in Abuja.Umar said that the agency identified seven critical weaknesses in the models, which allowed attackers to manipulate the system through indirect prompt injection.

Attackers can cause ChatGPT to execute unintended commands through normal browsing, summarisation or search actions.

“Some flaws also enable attackers to bypass safety filters using trusted domains, and exploit markdown rendering bugs to hide malicious content.

“That act can even poison ChatGPT’s memory so that injected instructions persist across future interactions,” she said.

Umar said that although OpenAI had addressed part of the issue, large language models still face challenges in distinguishing genuine user intent from malicious embedded data.

She said that the technique had embedded hidden instructions in webpages, online comments, or crafted URLs, which can mislead ChatGPT into executing unintended actions during routine browsing or search activities.

Umar said the vulnerabilities posed substantial risks, including unauthorised actions, information leakage, manipulated outputs and long-term behavioural influence due to memory poisoning.

She said that to avoid the risks, the agency urges organisations to limit or disable the browsing and summarisation of untrusted websites within enterprise environments.
Only enable ChatGPT capabilities like browsing or memory when operationally necessary,” she said

She also urged regular update and patch of the GPT-40 and GPT-5 models, to ensure that any known vulnerability is addressed.

Fix firewall issues
Meanhwile, theagency, through CERRT.NG, also issued an urgent warning about new security problems affecting Cisco firewall devices used across businesses, banks, government offices, and internet service providers.

According to the advisory shared on NITDA’s official X page on Monday, cybercriminals are now exploiting a fresh attack method targeting Cisco Secure Firewall ASA and Cisco Secure Firewall Threat Defense (FTD) systems. The flaw can forcibly reboot a device, causing unexpected network outages.

The agency explains that attackers are using older vulnerabilities as part of a new method that can make firewalls “restart without warning,” leading to instability and denial-of-service across affected networks.

Kaczynski:
what does nitda know?? their website is still stuck using php 2.0.


up to now 90% of the population cant afford Internet, whats their use case?? Nitda should be scraped

Kaczynski:
what does nitda know?? their website is still stuck using php 2.0.


up to now 90% of the population cant afford inteenet, whats their use case?? Nitda should be scraped

Kaczynski:
what does nitda know?? their website is still stuck using php 2.0.


up to now 90% of the population cant afford inteenet, whats their use case?? Nitda should be scraped

Kaczynski:
what does nitda know?? their website is still stuck using php 2.0.


up to now 90% of the population cant afford inteenet, whats their use case?? Nitda should be scraped

thesicilian:
You won't heed a simple warning now o, by the time you fall victim you'll start blaming your innocent village people.

omoredia:
Bunch of fools. People that didn't come up with anything are talking of flaws. Nigeria that is flawed from top to bottom una no see am

Redoil:
https://punchng.com/nitda-alerts-nigerians-on-chatgpt-flaws/

thesicilian:
You won't heed a simple warning now o, by the time you fall victim you'll start blaming your innocent village people.

shortgun:
Every invention in this world is a double-edged sword. For all the comfort and convenience technology has brought us, it has also stolen pieces of our safety, leaving us more exposed than we ever expected.