Published file metadata, source observations, indicators, and research history in one bounded catalog.
Sources represented on this page. Publication and observation dates describe the content; successful batch dates describe local collection. A recent batch does not certify complete coverage or current provider availability.
1 sources: 0 stale, 0 needing attention, 0 paused, 1 unverified.
Stale means older than twice the recorded collection interval, with a minimum of one hour; without an interval, the threshold is 24 hours. Cached content remains available while a feed is stale, paused, or unverified.
HF does a detailed play-by-play of the incident with a neat visualization, stopping AI attackers via content that triggers their guardrails, Mythos finds attacks on HAWK and AES
First reported Jul 30, 2026 14:30 UTCCatalog metadata updated Oct 08, 2026 03:53 UTCOpen evidence recordGoogle's deep dive on how threat actors are using AI, bypassing malicious skill scanning, using VS Code dev tunnels for command and control
First reported Jun 04, 2026 14:30 UTCCatalog metadata updated Oct 08, 2026 03:53 UTCOpen evidence recordPortswigger's James Kettle's HTTP Terminator, pretty crazy report about how threat actors were abusing Claude, how Cloudflare enforces code quality at scale
First reported Sep 17, 2026 14:30 UTCCatalog metadata updated Oct 08, 2026 03:53 UTCOpen evidence recordFull 38 page report from OpenAI on the incident, map your AWS environment, top 10 agent skill no no's
First reported Aug 27, 2026 14:30 UTCCatalog metadata updated Oct 08, 2026 03:53 UTCOpen evidence recordOSS tool to scan packages, agent configs, editors, and browser extensions for malware, tactics for evading cloud logging, a specification to generate your own custom agentic AI security scanning system
First reported Jun 18, 2026 14:30 UTCCatalog metadata updated Oct 08, 2026 03:53 UTCOpen evidence recordAnthropic and Meta models hacked third parties during testing, #collab-ing with an agent in an IR notebook, deep dive post on Figma's AI-powered code scanning
First reported Aug 07, 2026 14:30 UTCCatalog metadata updated Oct 08, 2026 03:53 UTCOpen evidence recordOSS tool to prevent supply chain attacks without client-side firewalls, OpenAI announces new GPT-5.5-Cyber, Codex Security plugin updates, and more, can AI agents compromise an AWS cyber range without tripping canaries?
First reported Jun 25, 2026 14:30 UTCCatalog metadata updated Oct 08, 2026 03:53 UTCOpen evidence recordThreat actor using open source harnesses to hack companies, how to use GitHub logs to find baddies, using LLMs to find novel Java deserialization gadgets
First reported Sep 24, 2026 14:30 UTCCatalog metadata updated Oct 08, 2026 03:53 UTCOpen evidence record100+ intentionally vulnerable AWS environments for practicing cloud attack paths, how OpenAI deploys Codex internally, Anthropic's update on bugs found and their open sourced harness
First reported May 28, 2026 14:30 UTCCatalog metadata updated Oct 08, 2026 03:53 UTCOpen evidence recordInteresting paper, LLM-powered hardening of the PHP ecosystem, security implications of the new MCP spec
First reported Jul 02, 2026 19:24 UTCCatalog metadata updated Oct 08, 2026 03:53 UTCOpen evidence recordA bug description is sufficient for AI to find it and write an exploit, cheat sheet on doing DFIR for GitHub, GitLab and more, and a paper on self-replicating, open weight agentic worms
First reported Sep 10, 2026 14:30 UTCCatalog metadata updated Oct 08, 2026 03:53 UTCOpen evidence recordWhy I joined OpenAI to lead Cyber efforts, playlist of the latest cloud security talks, AWS' supply chain best practices
First reported Jun 11, 2026 14:30 UTCCatalog metadata updated Oct 08, 2026 03:53 UTCOpen evidence recordGoogle's AI-powered web app scanner with deterministic validation, OSS tool to detect, prevent, and investigate risky AI agent behavior, NCSC: "One does not simply defend agentically"
First reported Oct 01, 2026 14:30 UTCCatalog metadata updated Oct 08, 2026 03:53 UTCOpen evidence recordWhen models decide to find 0-days instead of solving a benchmark, using LLMs to extract EDR logic, Google's AI security review skills and pipeline
First reported Jul 23, 2026 14:30 UTCCatalog metadata updated Oct 08, 2026 03:53 UTCOpen evidence recordModel finds 0-days to escape a QEMU/KVM VM, how to build a $500/month threat hunting agent, a decompiler benchmark and an experimental, LLM-written decompiler
First reported Sep 08, 2026 14:30 UTCCatalog metadata updated Oct 08, 2026 03:53 UTCOpen evidence recordHow Figma scales their detection and response, 1Password and Cloudflare on least privilege and identity for Agents, Uber's paper and OSS repo on monitoring and securing enterprise AI agents
First reported Aug 20, 2026 14:30 UTCCatalog metadata updated Oct 08, 2026 03:53 UTCOpen evidence recordDeep dive and timeline of HF from OpenAI, Portswigger shows how CSS in webmail clients can be weaponized, GitHub's platform improvements
First reported Aug 13, 2026 14:30 UTCCatalog metadata updated Oct 08, 2026 03:53 UTCOpen evidence recordDetecting and deceiving attackers with AI honeypots, detect supply chain attacks with GitHub Action canaries, the latest from Microsoft's new "Autonomous Code Security" team
First reported May 21, 2026 14:30 UTCCatalog metadata updated Oct 08, 2026 03:53 UTCOpen evidence recordAn MCP powered system that's continuously finding and reproducing vulns, improvements to Datadog's OSS malware hunting tool, Hakluke muses on the future of bug bounty
First reported Jul 09, 2026 14:30 UTCCatalog metadata updated Oct 08, 2026 03:53 UTCOpen evidence recordSurvey for AI-powered vulnerability finding harnesses, programmatically build complex decoy cloud environments, building hackbots
First reported Jul 16, 2026 14:30 UTCCatalog metadata updated Oct 08, 2026 03:53 UTCOpen evidence recordA filename, label, or report mention alone does not establish maliciousness. Observation dates describe cited sources; collection dates describe this local metadata catalog. No malware samples are stored, fetched, or executed by these pages.