it thought about zenity too hard :(
September 20, 2026 at 9:08 PM
it thought about zenity too hard :(
Researchers at security firm Zenity found more than a dozen flaws in AI browsers—and managed to get OpenAI’s Atlas to make an unauthorized Amazon purchase. www.wired.com/story/openai...
OpenAI’s Browser Could Be Hijacked to Spam Your WhatsApp Contacts
Researchers at security firm Zenity found more than a dozen flaws in AI browsers—and managed to get OpenAI’s Atlas to make an unauthorized Amazon purchase.
www.wired.com
August 5, 2026 at 11:36 PM
Researchers at security firm Zenity found more than a dozen flaws in AI browsers—and managed to get OpenAI’s Atlas to make an unauthorized Amazon purchase. www.wired.com/story/openai...
Salesforce AI agents spilled CRM data 🕵️♀️
Zenity Labs uncovered "SalesBleed," flaws allowing hijacked Salesforce AI agents to steal CRM data and phish contacts.
Another reminder that containing AI agents in the wild is proving harder than expected.
Zenity Labs uncovered "SalesBleed," flaws allowing hijacked Salesforce AI agents to steal CRM data and phish contacts.
Another reminder that containing AI agents in the wild is proving harder than expected.
September 26, 2026 at 6:40 PM
Salesforce AI agents spilled CRM data 🕵️♀️
Zenity Labs uncovered "SalesBleed," flaws allowing hijacked Salesforce AI agents to steal CRM data and phish contacts.
Another reminder that containing AI agents in the wild is proving harder than expected.
Zenity Labs uncovered "SalesBleed," flaws allowing hijacked Salesforce AI agents to steal CRM data and phish contacts.
Another reminder that containing AI agents in the wild is proving harder than expected.
(I made this fake dialog box using zenity. It's actually quite easy to use, zenity --info --message="whatever you want".
You can use some html tags like <b> and also \n to jump to a new line).
You can use some html tags like <b> and also \n to jump to a new line).
July 18, 2026 at 4:00 PM
(I made this fake dialog box using zenity. It's actually quite easy to use, zenity --info --message="whatever you want".
You can use some html tags like <b> and also \n to jump to a new line).
You can use some html tags like <b> and also \n to jump to a new line).
AI agents are 'gullible' and easy to turn into your minions
AI agents are 'gullible' and easy to turn into your minions
Zenity CTO demos 0-click AI agent exploits on stage at RSAC
RSA 2026 There's a very simple reason why just about every enterprise AI agent is vulnerable to zero-click attacks, according to Michael Bargury, CTO of AI security company Zenity.…
go.theregister.com
March 24, 2026 at 5:54 PM
AI agents are 'gullible' and easy to turn into your minions
AI agents are 'gullible' and easy to turn into your minions
AI agents are 'gullible' and easy to turn into your minions
Zenity CTO demos 0-click AI agent exploits on stage at RSAC
RSA 2026 There's a very simple reason why just about every enterprise AI agent is vulnerable to zero-click attacks, according to Michael Bargury, CTO of AI security company Zenity.…
go.theregister.com
March 26, 2026 at 1:56 AM
AI agents are 'gullible' and easy to turn into your minions
Z FB skupiny Slovní hračičkové:
Chlap, který má jednu ženu, by měl být žený.
Co se týče mnohoženství, tak ženatý má dvě, ženitý tři a dále jsou ženičitý, ženečný, ženový, ženistý a ženičelý.
Drahá s výše uvedenou definicí úplně nesouhlasí.
#láskyplno #manželské_etudy
Chlap, který má jednu ženu, by měl být žený.
Co se týče mnohoženství, tak ženatý má dvě, ženitý tři a dále jsou ženičitý, ženečný, ženový, ženistý a ženičelý.
Drahá s výše uvedenou definicí úplně nesouhlasí.
#láskyplno #manželské_etudy
March 31, 2024 at 11:45 AM
Z FB skupiny Slovní hračičkové:
Chlap, který má jednu ženu, by měl být žený.
Co se týče mnohoženství, tak ženatý má dvě, ženitý tři a dále jsou ženičitý, ženečný, ženový, ženistý a ženičelý.
Drahá s výše uvedenou definicí úplně nesouhlasí.
#láskyplno #manželské_etudy
Chlap, který má jednu ženu, by měl být žený.
Co se týče mnohoženství, tak ženatý má dvě, ženitý tři a dále jsou ženičitý, ženečný, ženový, ženistý a ženičelý.
Drahá s výše uvedenou definicí úplně nesouhlasí.
#láskyplno #manželské_etudy
NEW: Yep, more AIs are doing hacking stuff—but the systems still have plenty of flaws themselves.
Security researchers tricked OpenAI's web browser into spamming people's WhatsApp contacts and making unauthorized Amazon purchases
Security researchers tricked OpenAI's web browser into spamming people's WhatsApp contacts and making unauthorized Amazon purchases
OpenAI’s Browser Could Be Hijacked to Spam Your WhatsApp Contacts
Researchers at security firm Zenity found more than a dozen flaws in AI browsers—and managed to get OpenAI’s Atlas to make an unauthorized Amazon purchase.
www.wired.com
August 6, 2026 at 10:55 AM
NEW: Yep, more AIs are doing hacking stuff—but the systems still have plenty of flaws themselves.
Security researchers tricked OpenAI's web browser into spamming people's WhatsApp contacts and making unauthorized Amazon purchases
Security researchers tricked OpenAI's web browser into spamming people's WhatsApp contacts and making unauthorized Amazon purchases
The latest update for #Zenity includes "#Gartner Names Zenity a Market Shaper for #AI Application Security" and "The Agent Will See You Now: Why #Healthcare's AI Agent Boom Needs Visibility and Control".
#cybersecurity #lowcodesecurity #appsec https://opsmtrs.com/3GN6TxH
#cybersecurity #lowcodesecurity #appsec https://opsmtrs.com/3GN6TxH
Zenity
Design and implement governance policies, identify security risks, detect emerging threats and drive automatic mitigation and response.
opsmtrs.com
September 24, 2026 at 2:24 AM
The latest update for #Zenity includes "#Gartner Names Zenity a Market Shaper for #AI Application Security" and "The Agent Will See You Now: Why #Healthcare's AI Agent Boom Needs Visibility and Control".
#cybersecurity #lowcodesecurity #appsec https://opsmtrs.com/3GN6TxH
#cybersecurity #lowcodesecurity #appsec https://opsmtrs.com/3GN6TxH
AI agents are 'gullible' and easy to turn into your minions
AI agents are 'gullible' and easy to turn into your minions
Zenity CTO demos 0-click AI agent exploits on stage at RSAC
RSA 2026 There's a very simple reason why just about every enterprise AI agent is vulnerable to zero-click attacks, according to Michael Bargury, CTO of AI security company Zenity.…
go.theregister.com
March 23, 2026 at 5:53 PM
AI agents are 'gullible' and easy to turn into your minions
Research shows AI agents are highly vulnerable to hijacking attacks
Research shows AI agents are highly vulnerable to hijacking attacks
Experts from Zenity Labs demonstrated how attackers could exploit widely deployed AI technologies for data theft and manipulation.
buff.ly
August 14, 2025 at 2:12 AM
Research shows AI agents are highly vulnerable to hijacking attacks
Zenity Labs ontdekt nieuwe 'SalesBleed'-kwetsbaarheid in Salesforce Agentforce
Zenity Labs heeft een ernstige kwetsbaarheid genaamd SalesBleed ontdekt in Salesforce Agentforce, een AI-gestuurd verkoopgereedschap. Deze kwetsbaarheid stelde aanvallers in staat om gevoelige CRM-gegevens te s...
Zenity Labs heeft een ernstige kwetsbaarheid genaamd SalesBleed ontdekt in Salesforce Agentforce, een AI-gestuurd verkoopgereedschap. Deze kwetsbaarheid stelde aanvallers in staat om gevoelige CRM-gegevens te s...
Zenity Labs ontdekt nieuwe 'SalesBleed'-kwetsbaarheid in Salesforce Agentforce
Zenity Labs heeft een ernstige kwetsbaarheid genaamd SalesBleed ontdekt in Salesforce Agentforce, een AI-gestuurd verkoopgereedschap. Deze kwetsbaarheid stelde aanvallers in staat om gevoelige CRM-gegevens te stelen zonder dat er een inlogpoging, toegang tot een Salesforce-tenant of interactie van het slachtoffer vereist was. De aanval maakte gebruik van indirecte promptinjectie via de publiekelijk toegankelijke Salesforce Web-to-Lead-formulieren. Deze formulieren zijn bedoeld om verkoopleads van externe gebruikers te verzamelen en zijn opzettelijk niet geauthenticeerd. Een aanvaller kon een ogenschijnlijk normale lead indienen, maar dan met verborgen instructies in een veld dat door Agentf...
newsfacts.info
September 25, 2026 at 9:00 AM
Zenity Labs ontdekt nieuwe 'SalesBleed'-kwetsbaarheid in Salesforce Agentforce
Zenity Labs heeft een ernstige kwetsbaarheid genaamd SalesBleed ontdekt in Salesforce Agentforce, een AI-gestuurd verkoopgereedschap. Deze kwetsbaarheid stelde aanvallers in staat om gevoelige CRM-gegevens te s...
Zenity Labs heeft een ernstige kwetsbaarheid genaamd SalesBleed ontdekt in Salesforce Agentforce, een AI-gestuurd verkoopgereedschap. Deze kwetsbaarheid stelde aanvallers in staat om gevoelige CRM-gegevens te s...
hey it's me it's gitlab.gnome.org/GNOME/zenity
September 14, 2026 at 7:02 PM
hey it's me it's gitlab.gnome.org/GNOME/zenity
Hobble your AI agents to prevent them from hurting you too badly
Hobble your AI agents to prevent them from hurting you too badly
That's the main takeaway from the Zenity AI Agent Security Summit
Michael Bargury, CTO of AI security company Zenity, welcomed attendees to the company's AI Agent Security Summit on Wednesday with an unexpected admission.…
dlvr.it
October 9, 2025 at 7:31 AM
Hobble your AI agents to prevent them from hurting you too badly
3 Urgent Remote Marketing Jobs Found in Last 24h. Hot picks:
◆ Zenity | Partner Marketing, Director
◆ Location: United States
◆ Remote | Full Time
Grab the full list via link in bio!
◆ Zenity | Partner Marketing, Director
◆ Location: United States
◆ Remote | Full Time
Grab the full list via link in bio!
September 25, 2026 at 6:00 PM
3 Urgent Remote Marketing Jobs Found in Last 24h. Hot picks:
◆ Zenity | Partner Marketing, Director
◆ Location: United States
◆ Remote | Full Time
Grab the full list via link in bio!
◆ Zenity | Partner Marketing, Director
◆ Location: United States
◆ Remote | Full Time
Grab the full list via link in bio!
In further lethal trifecta news, here's a newly described attack against Cursor when combined with a Jira MCP simonwillison.net/2025/Aug/9/w...
When a Jira Ticket Can Steal Your Secrets
Zenity Labs describe a classic lethal trifecta attack, this time against Cursor, MCP, Jira and Zendesk. They also have a short video demonstrating the issue. Zendesk support emails are often …
simonwillison.net
August 9, 2025 at 5:19 AM
In further lethal trifecta news, here's a newly described attack against Cursor when combined with a Jira MCP simonwillison.net/2025/Aug/9/w...
August 2, 2026 at 6:33 AM
A simple video.
We Hacked Copilot Studio: The AI Agent Risk Hiding in Your Environment
YouTube video by Zenity
www.youtube.com
August 21, 2025 at 7:56 PM
A simple video.
The latest update for #Zenity includes "Zenity and Carahsoft Partner to Bring #AI Agent Security to Government Agencies" and "What Auditors and Regulators Are Starting to Ask About AI Agents".
#cybersecurity #lowcodesecurity #appsec https://opsmtrs.com/3GN6TxH
#cybersecurity #lowcodesecurity #appsec https://opsmtrs.com/3GN6TxH
Zenity
Design and implement governance policies, identify security risks, detect emerging threats and drive automatic mitigation and response.
opsmtrs.com
June 18, 2026 at 3:53 AM
The latest update for #Zenity includes "Zenity and Carahsoft Partner to Bring #AI Agent Security to Government Agencies" and "What Auditors and Regulators Are Starting to Ask About AI Agents".
#cybersecurity #lowcodesecurity #appsec https://opsmtrs.com/3GN6TxH
#cybersecurity #lowcodesecurity #appsec https://opsmtrs.com/3GN6TxH
Mają lepszą jakość obrazowania niż my. Pewnie ostatnie zenity zrzucają klisze na ziemie.
May 26, 2026 at 4:08 PM
Mają lepszą jakość obrazowania niż my. Pewnie ostatnie zenity zrzucają klisze na ziemie.
past week Microsoft & Google have been hacked through Copilot Studio and Gemini through prompt injections.
And they aren't alone. These systems leaks data and it's unlikely they can secure it.
And they aren't alone. These systems leaks data and it's unlikely they can secure it.
Zero-Click AI Hijacks Exposed: Copilot and Gemini Vulnerabilities at Black Hat 2025
At Black Hat 2025, Zenity researchers demonstrated zero-click prompt injection attacks that hijack AI agents like Microsoft Copilot and Google Gemini via malicious files, enabling silent data leaks wi...
www.webpronews.com
August 14, 2025 at 12:24 PM
past week Microsoft & Google have been hacked through Copilot Studio and Gemini through prompt injections.
And they aren't alone. These systems leaks data and it's unlikely they can secure it.
And they aren't alone. These systems leaks data and it's unlikely they can secure it.
Zenity, which develops a platform for securing AI agents, raised a $125M Series C led by Norwest Venture Partners, taking its total funding to ~$185M (Meir Orbach/CTech)
Main Link | Techmeme Permalink
Main Link | Techmeme Permalink
August 3, 2026 at 1:46 PM
Zenity, which develops a platform for securing AI agents, raised a $125M Series C led by Norwest Venture Partners, taking its total funding to ~$185M (Meir Orbach/CTech)
Main Link | Techmeme Permalink
Main Link | Techmeme Permalink