Goblin
News
AI news by
promptgoblins.ai
|
News
About
News
About
Filtered by:
prompt-injection
Clear
Titles
Summaries
April
7
Ramp Sheets AI Prompt Injection Enabled Silent Financial Data Exfiltration
Security
1
Apr 30
7
Ramp Sheets AI Prompt Injection Enabled Silent Financial Data Exfiltration
Security
· 1 src · Apr 30
Discuss
7
OpenAI Launches Chronicle: Screen-Aware Memory for Codex on macOS
Products
1
Apr 21
7
OpenAI Launches Chronicle: Screen-Aware Memory for Codex on macOS
Products
· 1 src · Apr 21
Discuss
6
AI Chatbots Now Replying to Airbnb Guests on Hosts' Behalf, Sparking Disclosure Questions
Enterprise
1
Apr 14
6
AI Chatbots Now Replying to Airbnb Guests on Hosts' Behalf, Sparking Disclosure Questions
Enterprise
· 1 src · Apr 14
Discuss
8
Vercel Claude Code Plugin Uses Prompt Injection to Collect Telemetry on All Projects
Security
1
Apr 10
8
Vercel Claude Code Plugin Uses Prompt Injection to Collect Telemetry on All Projects
Top
Security
· 1 src · Apr 10
Discuss
6
ClawKeeper: Real-Time Security Framework for Autonomous AI Agents
Security
1
Apr 5
6
ClawKeeper: Real-Time Security Framework for Autonomous AI Agents
Security
· 1 src · Apr 5
Discuss
7
Check Point Finds DNS Tunneling Flaw in ChatGPT Data Analysis Runtime
Security
1
Apr 4
7
Check Point Finds DNS Tunneling Flaw in ChatGPT Data Analysis Runtime
Security
· 1 src · Apr 4
Discuss
8
Claude Code Source Leak: Breach and Architectural Secrets Exposed
Updated
Security
9
Apr 3
8
Claude Code Source Leak: Breach and Architectural Secrets Exposed
Top
Security
· 9 srcs · Apr 3
Discuss
6
Opinion: A Privacy-First Local LLM Setup for the Agentic AI Era
Security
1
Apr 3
6
Opinion: A Privacy-First Local LLM Setup for the Agentic AI Era
Security
· 1 src · Apr 3
Discuss
6
Amazon Bedrock AgentCore Adds Domain Allowlist Filtering for AI Agent Web Access
Products
1
Apr 3
6
Amazon Bedrock AgentCore Adds Domain Allowlist Filtering for AI Agent Web Access
Products
· 1 src · Apr 3
Discuss
6
AWS GenAI Innovation Center Launches AIRI Governance Platform
Products
1
Apr 3
6
AWS GenAI Innovation Center Launches AIRI Governance Platform
Products
· 1 src · Apr 3
Discuss
6
Bessemer Venture Partners: Five AI Infrastructure Frontiers for 2026
Infra
2
Apr 3
6
Bessemer Venture Partners: Five AI Infrastructure Frontiers for 2026
Infra
· 2 srcs · Apr 3
Discuss
March
7
Northeastern Study: OpenClaw AI Agents Manipulated Into Self-Sabotage via Social Engineering
Safety
1
Mar 25
7
Northeastern Study: OpenClaw AI Agents Manipulated Into Self-Sabotage via Social Engineering
Safety
· 1 src · Mar 25
Discuss
6
Kagi Translate Goes Viral for LLM 'Language' Loophole
Safety
1
Mar 19
6
Kagi Translate Goes Viral for LLM 'Language' Loophole
Safety
· 1 src · Mar 19
Discuss
8
Snowflake Cortex Code CLI: Sandbox Escape via Indirect Prompt Injection
Security
1
Mar 18
8
Snowflake Cortex Code CLI: Sandbox Escape via Indirect Prompt Injection
Top
Security
· 1 src · Mar 18
Discuss
7
OpenClaw 'Lobster' Craze Reshapes China's AI Sector with Corporate Spinoffs, Government Grants, and Mass Adoption
Updated
Enterprise
6
Apr 6
7
OpenClaw 'Lobster' Craze Reshapes China's AI Sector with Corporate Spinoffs, Government Grants, and Mass Adoption
Enterprise
· 6 srcs · Apr 6
Discuss
Monday
7
Anthropic Releases Claude Opus 4.8 Amid RSP Policy Update Controversy
Updated
Models
2
1d ago
7
Anthropic Releases Claude Opus 4.8 Amid RSP Policy Update Controversy
Models
· 2 srcs · 1d ago
Discuss
6
AI Systems Meant to Prevent Downtime Are Now Causing New Outages
Enterprise
1
2d ago
6
AI Systems Meant to Prevent Downtime Are Now Causing New Outages
Enterprise
· 1 src · 2d ago
Discuss
Last Week
7
Hidden Prompt Injection in jqwik Targeted AI Coding Agents to Delete Tests and Code
Security
1
4d ago
7
Hidden Prompt Injection in jqwik Targeted AI Coding Agents to Delete Tests and Code
Security
· 1 src · 4d ago
Discuss
7
Anthropic Engineering: How Claude Agents Are Contained Across Products
Security
1
May 27
7
Anthropic Engineering: How Claude Agents Are Contained Across Products
Security
· 1 src · May 27
Discuss
2 Weeks Ago
7
Gemini Unexpectedly Dumps Its Full System Prompt to User
Security
1
May 21
7
Gemini Unexpectedly Dumps Its Full System Prompt to User
Security
· 1 src · May 21
Discuss
6
LangSmith Auth Proxy: Keeping Credentials Out of Agent Sandboxes
Products
1
May 21
6
LangSmith Auth Proxy: Keeping Credentials Out of Agent Sandboxes
Products
· 1 src · May 21
Discuss
8
AI Chatbots Spread Election Misinformation and Are Vulnerable to Deliberate Manipulation, Studies Find
Updated
Policy
2
May 20
8
AI Chatbots Spread Election Misinformation and Are Vulnerable to Deliberate Manipulation, Studies Find
Top
Policy
· 2 srcs · May 20
Discuss
8
Solo Operators Use Claude and GPT-4.1 to Breach Mexican Government, Exfiltrate 150 GB
Security
1
May 19
8
Solo Operators Use Claude and GPT-4.1 to Breach Mexican Government, Exfiltrate 150 GB
Security
· 1 src · May 19
Discuss
7
AudioHijack: Imperceptible Audio Attacks Hijack AI Voice Models with Up to 96% Success Rate
Security
1
May 18
7
AudioHijack: Imperceptible Audio Attacks Hijack AI Voice Models with Up to 96% Success Rate
Security
· 1 src · May 18
Discuss
3 Weeks Ago
6
OpenSquilla Launches Open-Source AI Agent Runtime to Cut Token Costs
Open Source
1
May 15
6
OpenSquilla Launches Open-Source AI Agent Runtime to Cut Token Costs
Open Source
· 1 src · May 15
Discuss
7
AI Safety Controls Remain Easy to Bypass, Researchers Warn
Safety
1
May 14
7
AI Safety Controls Remain Easy to Bypass, Researchers Warn
Safety
· 1 src · May 14
Discuss
6
Tübingen Researchers Propose Parallel-Stream Architecture to Unblock LLMs
Research
1
May 14
6
Tübingen Researchers Propose Parallel-Stream Architecture to Unblock LLMs
Research
· 1 src · May 14
Discuss
Last Month
7
Perplexity Personal Computer: Launch Details and Security Architecture Explained
Updated
Products
3
May 14
7
Perplexity Personal Computer: Launch Details and Security Architecture Explained
Products
· 3 srcs · May 14
Discuss
Filters
Signal
Title
Category
Sources
Posted
Discuss
