Local AI for Penetration Testing & Research
https://projectblack.io/blog/local-ai-for-cyber-security/
https://projectblack.io/blog/local-ai-for-cyber-security/
Research Blog | Project Black
Local AI for Penetration Testing & Research
How competent are local AI models for cyber security bug hunting and research?
π10β€4π2
The Biometric AuthToken Heist: Cracking PINs and Bypassing CE via a Long-Ignored Attack Surface
https://www.darknavy.org/blog/the_biometric_authtoken_heist/
https://www.darknavy.org/blog/the_biometric_authtoken_heist/
DARKNAVY Blog
The Biometric AuthToken Heist: Cracking PINs and Bypassing CE via a Long-Ignored Attack Surface
Modern Android devices make biometric authentication feel routine: a touch, a glance, and the device accepts that the user is present. Underneath that convenience is a security boundary that is easy to underestimate. Fingerprint and face authentication areβ¦
β€6
No need to be a Mythos to do offensive security
https://fuzzinglabs.com/wp-content/uploads/2026/06/Le-Hack-2026-Keynote-_-No-Need-to-be-a-Mythos-to-do-Offensive-security-Patrick-Ventuzelo-_-FuzzingLabs.pdf
https://fuzzinglabs.com/wp-content/uploads/2026/06/Le-Hack-2026-Keynote-_-No-Need-to-be-a-Mythos-to-do-Offensive-security-Patrick-Ventuzelo-_-FuzzingLabs.pdf
β€7π₯6
CitrixBleed To Infinity And Beyond (Citrix NetScaler Pre-Auth Memory Overread CVE-2026-8451)
https://labs.watchtowr.com/citrixbleed-to-infinity-and-beyond-citrix-netscaler-pre-auth-memory-overread-cve-2026-8451/
https://labs.watchtowr.com/citrixbleed-to-infinity-and-beyond-citrix-netscaler-pre-auth-memory-overread-cve-2026-8451/
watchTowr Labs
CitrixBleed To Infinity And Beyond (Citrix NetScaler Pre-Auth Memory Overread CVE-2026-8451)
Well, well, well - once again, the cat has dragged us in and spat us out.
Today, we find ourselves questioning the reality we sit within. Must it be so predictable, and why us? βBut watchTowr, what do you mean?β
Well, if youβre here, you likely fit intoβ¦
Today, we find ourselves questioning the reality we sit within. Must it be so predictable, and why us? βBut watchTowr, what do you mean?β
Well, if youβre here, you likely fit intoβ¦
Find Comment, Get Shell: Command Injection in dbtβs GitHub Actions
https://www.landh.tech/blog/20260701-find-comment-get-shell/
https://www.landh.tech/blog/20260701-find-comment-get-shell/
DuneSlide: Two Critical RCE vulnerabilities via Zero-Click Prompt Injection in Cursor IDE
https://www.catonetworks.com/blog/duneslide-two-critical-rce-vulnerabilities/
https://www.catonetworks.com/blog/duneslide-two-critical-rce-vulnerabilities/
Detecting Agentic Threats in Claude: Writing Rules on the Execution Layer
https://www.papermtn.co.uk/detecting-agentic-threats-in-claude-writing-rules-on-the-execution-layer/
https://www.papermtn.co.uk/detecting-agentic-threats-in-claude-writing-rules-on-the-execution-layer/
PaperMtn
Detecting Agentic Threats in Claude: Writing Rules on the Execution Layer
Detections for Claude on the execution layer: Sigma rules and a correlation runner that catch permission bypasses, rogue MCP servers, and more.
The Bug Bounty Singularity: Our Hackbot
https://josephthacker.com/hacking/2026/07/01/we-built-a-hackbot.html
https://josephthacker.com/hacking/2026/07/01/we-built-a-hackbot.html
β€4π€2π1
Reading Contact Photos Without READ_CONTACTS: A Google Messages Confused Deputy Bug
https://blog.devploit.dev/posts/google-messages-avatarcontentprovider-contacts-bypass/
https://blog.devploit.dev/posts/google-messages-avatarcontentprovider-contacts-bypass/
devploit / blog
Reading Contact Photos Without READ_CONTACTS: A Google Messages Confused Deputy Bug
Analysis of a fixed Google Messages vulnerability that exposed contact photos without READ_CONTACTS, covering its root cause and responsible disclosure.
β€8
β€1
How I Chained an Open Redirect into Email Leak and Got $1,337 from Google
https://xlsize0bruh.medium.com/how-i-chained-an-open-redirect-into-email-leak-and-got-1-337-from-google-c8a4655677a2
https://xlsize0bruh.medium.com/how-i-chained-an-open-redirect-into-email-leak-and-got-1-337-from-google-c8a4655677a2
Medium
How I Chained an Open Redirect into Email Leak and Got $1,337 from Google
Who Am I?
π12β€8
Confused Deputy: Google IdP Universal Account Takeover via Device Code Flow Hijacking
https://weirdmachine64.github.io/research/google-oauth-device-code-hijacking.html
https://weirdmachine64.github.io/research/google-oauth-device-code-hijacking.html
weirdmachine64
Confused Deputy: Google IdP Universal Account Takeover via Device Code Flow Hijacking // weirdmachine64
RFC 8628's device authorization grant lets a TV or CLI
β€5
How to use Claude Code for Bug Bounty: find fast, validate manually
https://www.yeswehack.com/learn-bug-bounty/llm-series-claude
https://www.yeswehack.com/learn-bug-bounty/llm-series-claude
π10β€5π3π2
WP2SHELL: PRE AUTHENTICATION RCE IN WORDPRESS CORE
https://slcyber.io/research-center/wp2shell-pre-authentication-rce-in-wordpress-core/
https://slcyber.io/research-center/wp2shell-pre-authentication-rce-in-wordpress-core/
www.slcyber.io
wp2shell: Pre Authentication RCE in WordPress Core
Critical issue discovered in WordPress Core affecting the majority of WordPress-built sites. A pre-authentication Remote Code Execution (RCE) that can be used by attackers to run malicious code to steal data or seize control without requiring login details.
β€9π3
Language Model Security Database
A comprehensive collection of LLM vulnerabilities, curated from cutting-edge research papers and real-world discoveries.
https://www.promptfoo.dev/lm-security-db
A comprehensive collection of LLM vulnerabilities, curated from cutting-edge research papers and real-world discoveries.
https://www.promptfoo.dev/lm-security-db
www.promptfoo.dev
LLM Security Database
Evidence-backed security research, model evaluations, mitigations, and primary-source papers.
β€8π4
Exploit brokers pay $500,000 for a WordPress RCE. I found one with GPT5.6 Sol Ultra and $25
https://slcyber.io/research-center/exploit-brokers-pay-500000-for-a-wordpress-rce-i-found-one-with-gpt5-6/
https://slcyber.io/research-center/exploit-brokers-pay-500000-for-a-wordpress-rce-i-found-one-with-gpt5-6/
www.slcyber.io
Exploit brokers pay $500,000 for a WordPress RCE. I found one with GPT5.6 Sol Ultra and $25
Adam Kues used a $200 GPT5.6 Sol Ultra subscription to discover a pre-authentication SQL injection and full RCE exploit chain in WordPress Core β a chain that chains a batch API desync, cache poisoning, changeset abuse, and hook injection into a completeβ¦
β€7π4π₯4
β€6
Securing GitHub: Wiz Research uncovers Remote Code Execution in GitHub.com and GitHub Enterprise Server (CVE-2026-3854)
https://www.wiz.io/blog/github-rce-vulnerability-cve-2026-3854
https://www.wiz.io/blog/github-rce-vulnerability-cve-2026-3854
wiz.io
GitHub RCE Vulnerability: CVE-2026-3854 Breakdown | Wiz Blog
A CVSS 8.7 vulnerability in GitHub Enterprise Server allows remote code execution. Read the threat brief and find vulnerable GHES instances from Wiz.
π7β€5π4π₯4
A Shell Is Worth A Thousand Images: Bing Images RCEs
https://xbow.com/blog/bing-images-rce-vulnerabilities
https://xbow.com/blog/bing-images-rce-vulnerabilities
β€4π3
From a βHey, {name} πβ Banner to Full Account Takeover | Chaining 4 Bugs Through a Rewards WebView
https://medium.com/@bag0zathev2/from-a-hey-name-banner-to-full-account-takeover-chaining-4-bugs-through-a-rewards-webview-f89a2b0f830f
https://medium.com/@bag0zathev2/from-a-hey-name-banner-to-full-account-takeover-chaining-4-bugs-through-a-rewards-webview-f89a2b0f830f
Medium
From a βHey, {name} πβ Banner to Full Account Takeover | Chaining 4 Bugs Through a Rewards WebView
Hey folks π Hope you are doing great today! β€
β€13