Anthropic launches OSS Scanner, a free opt-in vulnerability scanner for critical open-source projects
Anthropic has launched OSS Scanner, a free, opt-in vulnerability scanner for critical open-source projects. It runs the company's strongest models, including Claude Mythos, against enrolled codebases, and reports go straight to maintainers without human review.
Anthropic has launched OSS Scanner, a free, opt-in vulnerability scanner for critical open-source projects, according to a MarkTechPost report published October 25, 2026.
What it does
The Anthropic OSS Scanner runs the company's strongest models, including Claude Mythos, against enrolled codebases. Projects must opt in to be scanned. The service is free.
How reports are handled
Reports go straight to maintainers without human review. According to the report, that design delivers faster findings but shifts triage work onto project teams.
The report's summary also references an October 8 date and an interval of 11 days, but the details of that reference were not available in the summary text.
Details not yet available
Pricing is free, as stated. Further details on eligibility criteria, supported languages, rate limits, enrollment process and which Claude Mythos version is used have not been disclosed in the available summary.
What this means
Skipping human review before reports reach maintainers speeds up the path from detection to disclosure. The report states the cost of that choice plainly: triage work moves to the project teams that receive the findings. For maintainers weighing enrollment, the opt-in structure means that tradeoff is a decision they make for their own project.
Related Articles
Anthropic: Claude found 493 attack-surface issues across 25 open-source projects, led by OpenSSH fixes
Anthropic published early results on using Claude to map and reduce software attack surface. Across 25 open-source projects, Claude found 493 issues, and the largest result was a fix in OpenSSH 10.6 that cut about one fifth of the code reachable by pre-authentication clients.
Anthropic: unreleased model halted attacks in 67% of replays, Opus 5.5 in 10%
Anthropic says an unreleased internal model outperforms Mythos 5.1 in both capability and alignment. In replayed logs from a UK AISI cybersecurity test, it stopped ongoing attacks on its own in 67 percent of cases, versus 10 percent for Opus 5.5.
Anthropic Says Claude Proved Security Properties for 239 Entry Points Across 123 Libraries
Anthropic published research on October 22, 2026, reporting that Claude produced machine-checked formal proofs of security properties at the RISC-V assembly level. The proofs cover 239 fuzz-test entry points across 123 open-source libraries, in a collaboration with Theorem.
Anthropic's Jack Clark moves self-improving AI forecast to 2027 on TasteVal results
Anthropic co-founder Jack Clark now says recursive self-improvement could be possible as early as 2027, up from his earlier estimate of 2028. The shift follows TasteVal, a P-Zero Research benchmark in which Anthropic's Opus 5.5 reached expert-level scores with less than half the compute of a 24-person human baseline.
Comments
Loading...