Notifications
Clear all
Topic starter
10/07/2026 9:13 pm
TL;DR: Anthropic’s Project Glasswing showed that its Claude Mythos Preview model could chain multiple vulnerabilities into working exploit paths, scoring 83.1% on CyberGym and finding thousands of high-severity flaws, according to JupiterOne’s analysis of the announcement. The real shift is that security teams must now govern asset context and exploit chains, not just CVSS severity.
NHIMG editorial — based on content published by JupiterOne: Project Glasswing proves that "just patch the criticals" is dead. Here's what comes next
By the numbers:
- Project Glasswing is a $100 million cybersecurity initiative that uses an unreleased AI model called Claude Mythos Preview to find and fix critical software vulnerabilities before attackers can exploit them.
- Roughly 50 organizations in total have access to the program.
- Anthropic launched the initiative on April 7, 2026, backed by twelve major technology and finance companies.
Questions worth separating out
Q: What breaks when vulnerability management is based only on CVSS scores?
A: CVSS-only prioritisation breaks when several lower-scoring flaws can be combined into a complete exploit path.
Q: Why do AI-assisted attackers change vulnerability prioritisation?
A: AI-assisted attackers can test many combinations much faster than human teams can patch, which makes vulnerability chaining practical at scale.
Q: How do security teams know if contextual vulnerability management is working?
A: It is working when teams can answer three questions quickly: what can reach this asset, what identities does it trust, and what can an attacker reach from it if it is compromised.
Practitioner guidance
- Map exploit paths across connected assets Build queries that start with internet-facing weaknesses and trace reachable systems, data stores, and privileged identities.
- Treat service accounts as exposure amplifiers Review whether over-permissioned service accounts allow a vulnerable host to move laterally or reach sensitive data.
- Inventory AI agents as first-class assets Document every sanctioned and shadow AI agent, then tie each one to credentials, API connections, and reachable systems.
What's in the full article
JupiterOne's full article covers the operational detail this post intentionally leaves for the source:
- How the graph model maps vulnerabilities, identities, permissions, and asset relationships in practice
- Example J1QL queries for finding exploitable chains across production systems and service accounts
- What JupiterOne's AI Control Author and CCM workflows look like in a working environment
- How the MCP Server is positioned for secure AI-powered security workflows
👉 Read JupiterOne's analysis of Project Glasswing and vulnerability chaining →
AI agent vulnerability chains: what IAM and security teams need now?
Explore further
10/07/2026 9:35 pm
Patch-only vulnerability management is no longer a sufficient operating model. The old model assumes risk can be reduced by ranking individual flaws and clearing the critical queue first. That assumption fails when AI can chain several non-critical issues into a single exploit path faster than human triage cycles can react. The implication is that vulnerability governance has to shift from item-level severity to path-level exposure.
A few things that frame the scale:
- 98% of companies plan to deploy even more AI agents within the next 12 months, despite documented rogue behaviour in 80% of current deployments, according to AI Agents: The New Attack Surface report.
- Only 52% of companies can track and audit the data their AI agents access, leaving 48% with a complete blind spot for compliance and breach investigation.
A question worth separating out:
Q: What should teams do when AI agents become part of the attack surface?
A: Treat AI agents as non-human identities with explicit ownership, permissions, and data paths. Then review whether any agent can access systems or secrets that would turn a compromise into broader exposure. If the answer is unclear, the agent is already part of your attack surface and needs governance immediately.
👉 Read our full editorial: AI agent attack chains make patch-only vulnerability management obsolete
