Anthropic Petri open-source auditing tool launch for risky AI interaction testing
Security Tool/Service
Summary
Hide ▲
Show ▼
Anthropic released Petri, an open-source auditing tool that expands practical AI safety testing for risky model behaviors. The tool is designed to probe interactions involving deception, sycophancy, user delusion, harmful requests, and self-perseveration. Its release matters because it gives researchers a repeatable way to evaluate target models with automated multi-turn conversations and judge scoring.
Related Happenings
Anthropic Project Glasswing expands Claude Mythos Preview access
Security Tool/Service
H score54
First: 03.06.2026 12:30
Last: 03.06.2026 12:30
Sources 1
About this happening:
**Anthropic** expanded **Project Glasswing** on **June 2**, extending **Claude Mythos Preview** to **150 additional organizations** and widening a security-focused AI program used...
Anthropic Project Glasswing expands Claude Mythos Preview access
Security Tool/ServiceAbout this happening: **Anthropic** expanded **Project Glasswing** on **June 2**, extending **Claude Mythos Preview** to **150 additional organizations** and widening a security-focused AI program used...
Microsoft MDASH enters limited private preview for AI-driven vulnerability discovery at scale
Security Tool/Service
H score26
First: 13.05.2026 16:46
Last: 13.05.2026 16:46
Sources 1
About this happening:
Microsoft's **MDASH** has entered **limited private preview**, adding a new **AI-driven vulnerability discovery** service that can validate and prove exploitable defects at scale....
Microsoft MDASH enters limited private preview for AI-driven vulnerability discovery at scale
Security Tool/ServiceAbout this happening: Microsoft's **MDASH** has entered **limited private preview**, adding a new **AI-driven vulnerability discovery** service that can validate and prove exploitable defects at scale....
Google GTIG analysis of adversary AI use for exploit development and attack orchestration
Technical Analysis
H score33
First: 11.05.2026 16:00
Last: 11.05.2026 16:00
Sources 1
About this happening:
**Google Threat Intelligence Group** published findings showing **adversaries using AI** for **exploit development** and **attack orchestration**, signaling that model-assisted tr...
Google GTIG analysis of adversary AI use for exploit development and attack orchestration
Technical AnalysisAbout this happening: **Google Threat Intelligence Group** published findings showing **adversaries using AI** for **exploit development** and **attack orchestration**, signaling that model-assisted tr...
Prominent cybercrime threat actors AI-assisted zero-day exploitation campaign
Campaign
H score30
First: 11.05.2026 16:00
Last: 11.05.2026 16:00
Sources 1
About this happening:
An **AI-assisted zero-day exploitation campaign** was planned by **prominent cybercrime threat actors**, but the effort was **disrupted before deployment** and did not reach its i...
Prominent cybercrime threat actors AI-assisted zero-day exploitation campaign
CampaignAbout this happening: An **AI-assisted zero-day exploitation campaign** was planned by **prominent cybercrime threat actors**, but the effort was **disrupted before deployment** and did not reach its i...
Widespread exposure and misconfiguration in self-hosted AI infrastructure
Trend
H score76
First: 05.05.2026 13:30
Last: 05.05.2026 13:30
Sources 1
About this happening:
A large-scale measurement found **self-hosted AI infrastructure** was being deployed with **widespread exposure and no authentication**, creating a broad risk of data theft, workf...
Widespread exposure and misconfiguration in self-hosted AI infrastructure
TrendAbout this happening: A large-scale measurement found **self-hosted AI infrastructure** was being deployed with **widespread exposure and no authentication**, creating a broad risk of data theft, workf...
Timeline
-
08.10.2025 10:16 2 articles · 9mo ago
Anthropic launches Petri open-source auditing tool
Industry Or Public Sector UpdateAnthropic releases Petri, a short-form name for the Parallel Exploration Tool for Risky Interactions, as an open-source auditing tool for AI safety research and target-model testing. The tool uses an automated agent to run diverse multi-turn conversations with simulated users and tools, then scores the resulting transcripts so researchers can evaluate model behaviors such as deception, sycophancy, encouragement of user delusion, cooperation with harmful requests, and self-perseveration.
Show sources
- OpenAI Disrupts Russian, North Korean, and Chinese Hackers Misusing ChatGPT for Cyberattacks — thehackernews.com — 08.10.2025 10:16
- OpenAI Disrupts Russian, North Korean, and Chinese Hackers Misusing ChatGPT for Cyberattacks — thehackernews.com — 08.10.2025 10:16