Prompt Injection

Feeds to Scour
SubscribedAll
Scoured 125 posts in 34.2 ms

Brain-Prompt Injection: A Route-Safety Audit for BCI-LLM Agents

 🛡️AI Security  Content type: Academic
arxiv.org·
Less-relevant results

The Meta hack shows there’s more to AI security than Mythos

 🔓Hacking  Content type: News

Risky Business #841 -- Microsoft gets owned and 0day'd

 🧬Mythos
risky.biz·

QORIS-AI/knox: Security enforcement plugin for Claude Code. Blocks dangerous commands, audits every tool call, detects prompt injection.

 🔌Claude Plugins  Content type: Code
github.com··Hacker News

OpenAI govt stake 🇺🇸, Google compute deal 🚀, Microsoft Scout launch 🤖

 🤖AI
tldr.tech·

PRISM: Recovering Instruction Sets from Language Model Activations

 🛡️AI Security  Content type: Academic
arxiv.org·

Your AI Agent Is Not a Security Boundary

 💻Coding Agents
pub.towardsai.net
·

Caught in the Act(ivation): Toward Pre-Output and Multi-Turn Detection of Credential Exfiltration by LLM Agents

 🕳LLM Vulnerabilities  Content type: Academic
arxiv.org·

Under Violet

 🛡️AI Security
lesswrong.com·

OpenAI Rolls Out Lockdown Mode to Fight Prompt Injection Attacks

 🛡️AI Security  Content type: News
pcmag.com·

Mini Shai-Hulud, Miasma, and Hades Worms Target Bioinformatics and MCP Developers via Malicious PyPI Wheels

 🤖Agent Protocols  Content type: Blog
socket.dev··Hacker News

What If Prompt Injection Never Left? Exploring Cross-Session Stored Prompt Injection in Agentic Systems

 🛡️AI Security  Content type: Academic
arxiv.org·

Defending Jailbreak Attacks on Large Language Models via Manifold Trajectory Kinetics

 🕳LLM Vulnerabilities  Content type: Academic
arxiv.org·

I built an email agent to triage bogus security reports

 💻Claude Code  Content type: Blog

QFM116: Irresponsible AI Reading List — May 2026

 🛡️AI Security  Content type: Blog

Fixing the Failure of the Reevo

 🕳LLM Vulnerabilities
hackaday.com·

Tracing Eval-Awareness Emergence Through Training of OLMo 3

 🆕New AI
lesswrong.com·

Context-Fractured Decomposition Attacks on Tool-Using LLM Agents: Exploiting Artifact Provenance Gaps

 🕳LLM Vulnerabilities  Content type: Academic
arxiv.org·

Show HN: Jo – AI-native language to catch prompt injection at compile-time

 🔓Open Source Software  Content type: Code
github.com··Hacker News

Anthropic's most powerful model comes with a kill switch aimed at you

 🎭Claude
boingboing.net·

No more posts from emschwartz's subscribed feeds.

Sign up or log in to see more results

Keyboard Shortcuts

Navigation

Next / previous item
j/k
Open post
oorEnter
Preview post
v

Post Actions

Love post
a
Like post
l
Dislike post
d
Undo reaction
u
Save / unsave
s

Recommendations

Add interest / feed
Enter
Not interested
x

Go to

Home
gh
Interests
gi
Feeds
gf
Likes
gl
History
gy
Changelog
gc
Settings
gs
Browse
gb
Search
/

General

Show this help
?
Submit feedback
!
Close modal / unfocus
Esc

Press ? anytime to show this help