Is Anthropic's Glasswing finding real vulnerabilities?

Glasswing has produced 442 CVEs credited to Anthropic in seven months, so a share of its findings are real and tracked. VulnCheck notes that only two of those CVEs are known to be exploited in the wild, and that Anthropic's own disclosure ledger lists 1,654 duplicates and 419 withdrawn entries alongside just 217 fixes.

How accurate were the Glasswing reports curl received?

curl received 45 Glasswing reports and has published 34 of them. Of those, VulnCheck counts 19 marked not a vulnerability, 6 confirmed as low severity, and 9 still awaiting assessment. Garrity derives a 55.9% false positive rate from the published set, with 17.6% confirmed as genuine findings so far.

What should an open-source maintainer do about AI-generated vulnerability reports?

Garrity recommends that maintainers copy curl and publish low and medium severity AI-generated findings as public issues. Publishing them makes the real volume and accuracy of the reports visible to everyone, rather than leaving each project to absorb the triage privately. Anthropic sends OSS Scanner reports without human review, so the receiving project does the filtering.

INFOResearch Lab safety

VulnCheck: 442 CVEs from Anthropic's Glasswing, two exploited

Anthropic's AI vulnerability finder has produced 442 CVEs in seven months, and VulnCheck says maintainers absorb the triage cost.

November 9, 2026 · VulnCheck · Research by Patrick Garrity

Project Glasswing

VulnCheck title card for the Glasswing seven-month review

INFOResearch

VulnCheck counts 442 CVEs credited to Anthropic's Glasswing effort in seven months and says two are known to be exploited. Anthropic's ledger shows 217 findings fixed, against 1,654 duplicates and 419 withdrawn.

01What happened

Patrick Garrity of VulnCheck published a seven-month review of Project Glasswing, Anthropic's AI vulnerability-finding effort, on November 9, 2026. The review tracks 442 CVEs credited to Anthropic, about 63 a month, which Garrity puts at roughly 0.5% of the 93,450 CVEs published this year. VulnCheck lists two of those CVEs as known to be exploited.

02How it works

Glasswing findings reach maintainers through Anthropic's self-service OSS Scanner, which Anthropic says sends model-generated reports without human review. Triage therefore lands on the receiving project rather than on Anthropic. Garrity argues the published counts do not line up: Anthropic's disclosure ledger records 217 findings as fixed while listing 1,654 duplicates and 419 withdrawn entries.

03Who is affected

Open-source maintainers whose projects receive OSS Scanner reports carry the triage load, not Anthropic. curl is the worked example in the review, having received 45 reports, most of whose published entries were closed as not vulnerabilities. The per-project breakdown is in the table below.

04What to do

Follow curl's lead and publish low and medium severity AI-generated findings as public issues, which Garrity encourages so that the volume and accuracy of the reports stay visible. Treat a model-generated report as unreviewed until a human confirms it.

Measured results

Share of September ledger findings rated critical or high

Claude's own severity ratings against the maintainers' ratings of the same findings

Result	Score
Rated by Claude	91.5%
Rated by maintainers	51.3%

Scale 0 to 100% · Source: vulncheck.com, as published

Questions people ask

Is Anthropic's Glasswing finding real vulnerabilities?: Glasswing has produced 442 CVEs credited to Anthropic in seven months, so a share of its findings are real and tracked. VulnCheck notes that only two of those CVEs are known to be exploited in the wild, and that Anthropic's own disclosure ledger lists 1,654 duplicates and 419 withdrawn entries alongside just 217 fixes.
How accurate were the Glasswing reports curl received?: curl received 45 Glasswing reports and has published 34 of them. Of those, VulnCheck counts 19 marked not a vulnerability, 6 confirmed as low severity, and 9 still awaiting assessment. Garrity derives a 55.9% false positive rate from the published set, with 17.6% confirmed as genuine findings so far.
What should an open-source maintainer do about AI-generated vulnerability reports?: Garrity recommends that maintainers copy curl and publish low and medium severity AI-generated findings as public issues. Publishing them makes the real volume and accuracy of the reports visible to everyone, rather than leaving each project to absorb the triage privately. Anthropic sends OSS Scanner reports without human review, so the receiving project does the filtering.

Sources 4 links, all fetched

1vulncheck.comVulnCheck Review
2red.anthropic.comAnthropic Ledger
3anthropic.comOSS Scanner Post
4github.comCredited CVE Tracker