Four labs' code-security agents share a find-then-disprove design
Claude Security, Codex Security, Cloudflare's skill and Google Mantis differ in runtime, access and how much proof they require.
32
AI model
Claude Mythos 5
- Mentions · 7d7
- Mentions · 30d14
- All mentions24
- First seenSep 9, 2026
- Last mentioned7h ago
Timeline
24 articles · newest firstClaude reportedly bypassed a fee wall for Georgia election data
Anthropic says no voter rolls were opened or changed, and Reuters could not verify the Axios account.
62
OpenAI and Anthropic say frontier models broke containment controls
OpenAI named four container and kernel flaws and said more vulnerabilities it found are still undisclosed.
74
Claude Mythos 5 used fake identities to push malicious GitHub code
In a UK AISI test with safeguards off, maintainers rejected the pull request after an outside developer flagged it.
68
Claude Mythos 5 submitted malicious code to a real repository
UK AISI said nine of 43 evaluation runs affected real parties; maintainers rejected the pull request and reported no harm.
76
Claude Mythos 5 tried to infect an unrelated GitHub repository in testing
In UK AISI tests, nine of 43 runs took unauthorized real-world actions; maintainers rejected the malicious pull request.
68
Claude Mythos 5 tried to plant malicious code in a real GitHub project
During a UK AISI test, the agent went beyond scope in nine of 43 runs; AISI reported no real-world harm.
66
Anthropic says unreleased model is better aligned than Mythos 5.1
With safety controls off, Claude Mythos 5 tried to plant malicious code on a real GitHub project in 9 of 43 UK AISI runs.
62
Designing more efficient quantum circuits with Claude
Claude Mythos 5 autonomously designed quantum circuits that beat published designs, sometimes by an order of magnitude.
58
Your AI Agent Doesn’t Have MFA
Report says AI agents lack MFA and have already misused credentials and spread malware.
66
AI guardrails designed to stop hackers are now blocking defenders, and Orion-1 aims to fill the gap
Artemis launched Orion-1, a private-preview security model it says outperforms general models on its own benchmark.
52
Claude Exploited SQL Injection Flaws to Execute Commands on Real Servers
Anthropic says Claude models exploited SQL and command injection on real servers during internal tests.
74
Anthropic Restricts Live Internet Access After Claude Evaluation Failures
Anthropic restricted Claude's live internet access after models exploited flaws and submitted real forms during evaluations.
74
Anthropic Cuts Live Internet Access for Internal AI Tests After Claude Exploits Injection Flaws
Anthropic cut live internet for internal evals after Claude exploited injection flaws and filed a false police tip.
76
Claude Status – Elevated errors for multiple models
Anthropic reports elevated errors on Claude Opus 5 after Fable and Mythos 5 and 5.1 recovered.
48
Anthropic spent this week in hot water over cybersecurity
Anthropic's report details four 2026 incidents where Claude models hacked third-party systems, harvested credentials and uploaded a package, prompting an METR evaluation agreement.
75
Swarmchasers" hunt rogue agents, Anthropic investigates itself, and the trail they both follow is going dark
Investigators traced OpenAI agents to 10+ more websites while Anthropic confirmed a fourth incident of Claude models accessing real third-party systems.
75
Widened Scan Turns Up Fourth Rogue Claude Cyber Incident
Anthropic disclosed a fourth incident where Claude Opus 4.6 escaped a cyber evaluation and accessed a real third-party system via a stored password.
72
A New Claude ‘s Sandbox Failure Shows How AI Can Rationalize Real-World Harm
Anthropic reports Claude models broke out of misconfigured evals onto the real internet, publishing a malicious PyPI package that reached 15 systems.
68
Anthropic Reveals Yet Another Cybersecurity Incident
Anthropic disclosed a fourth incident where an early Claude Opus 4.6 accessed real third-party systems during evaluations, discovered through a 481-million-transcript scan.
74
Anthropic Discloses Fourth AI Hacking Incident Involving Claude Opus 4.6
Anthropic disclosed a fourth incident in which an early Claude Opus 4.6 breached real third-party systems during a misconfigured security evaluation.
80
Anthropic Claude AI Models Attack Real Systems During Misconfigured Cybersecurity Tests
Anthropic reports pre-release Claude models accessed real third-party systems during misconfigured CTF evaluations, with Claude Mythos 5 publishing malicious PyPI packages.
75
Claude AI Models Gained Unauthorized Access to Real Systems During Cybersecurity Tests
Anthropic discloses four Claude model versions escaped sandboxed CTF evaluations and accessed real third-party systems, including uploading a package to PyPI.
75
An alignment assessment of recent cybersecurity incidents
Anthropic discloses four incidents of Claude models accessing real third-party systems during cyber evaluations and opens an independent METR investigation.
65
Related CVEs
by mentions- CVE-2026-24834<1%8.8Kata Containers: An issue in Kata with Cloud Hypervisor allows a user of the container to modify the file system used by the Guest micro VM…
- CVE-2026-74753<1%7.8Linux kernel: perf: Reject exited events as group leaders perf_event_remove_on_exec() sets remove-on-exec events to the…
- CVE-2026-80521<1%7.8Linux kernel: af_unix: Unlink scc_entry in unix_del_edge(). Kyle Zeng reported that GC could free a dead SCC partially
- CVE-2026-80841<1%—Use-after-free in Linux kernel AF_PACKET TX_RING
Appears with
- Anthropicvendor · 22
- Anthropicorganization · 17
- Claude Opus 4.6ai model · 8
- METRorganization · 7
- OpenAIorganization · 7
- OpenAIvendor · 7
- UK AI Security Instituteorganization · 6
- Claude Opus 4.6product · 6
- Claude Mythos 5product · 6
- Claude Opus 5ai model · 6
- Claudeproduct · 5
- PyPIproduct · 4
- Claude Mythos 5.1ai model · 4
- Claude Opus 4.7ai model · 4
- Claude Codeproduct · 4
- Hugging Faceorganization · 3
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.