Technology · Paperclip AI
Paperclip AI Paperclip vulnerabilities
Updated . Rebuilt every hour.
Junglewise Threat Intelligence has tracked 12 vulnerabilities in Paperclip AI Paperclip: 0 in the last 7 days and 1 in the last 90 days, 3 of them critical and 0 exploited in the wild. The most recent, CVE-2026-77087, was published on 21 August 2026.
- Last 7 days
- 0
- Last 90 days
- 1
- Critical, all time
- 3
- Exploited in the wild
- 0
Latest Paperclip AI Paperclip vulnerabilities
- CVE-2026-77087: Paperclip DNS rebinding remote code executioncriticalCVSS 9.6EPSS 0.6%
- Paperclip cross-tenant agent API key IDOR in /agents/:id/keyslowCVSS 3.1
- Paperclip stored XSS in MarkdownBody via javascript: URLslowCVSS 3.1
- Paperclip Stored XSS in MarkdownBody via URL transform bypassmediumCVSS 5.4
- Paperclip cross-tenant agent API token minting in agent routescriticalCVSS 9.9
- Paperclip OS command injection in execution workspace cleanuplowCVSS 3.1
- Paperclip improper access control in codex_local inherits OpenAI Gmail connectorshighCVSS 8.7
- Paperclip arbitrary code execution in workspace runtime servicelowCVSS 3.1
- CVE-2026-41208: Paperclip: Privilege Escalation via Agent-Controlled workspaceStrategy.provisionCommand Leading to OS Command ExecutionhighCVSS 8.8EPSS 0.8%
- Paperclip arbitrary file read via adapterConfig in Claude adaptermediumCVSS 6.5
- Paperclip arbitrary file read via agent-controlled instructionsFilePathlowCVSS 3.1
- CVE-2026-41679: paperclip Vulnerable to Unauthenticated Remote Code Execution via Import Authorization BypasscriticalCVSS 10EPSS 7.4%
Most severe Paperclip AI Paperclip vulnerabilities
Exploited in the wild first, then by severity and CVSS score.
- CVE-2026-41679: paperclip Vulnerable to Unauthenticated Remote Code Execution via Import Authorization BypasscriticalCVSS 10EPSS 7.4%
- Paperclip cross-tenant agent API token minting in agent routescriticalCVSS 9.9
- CVE-2026-77087: Paperclip DNS rebinding remote code executioncriticalCVSS 9.6EPSS 0.6%
- CVE-2026-41208: Paperclip: Privilege Escalation via Agent-Controlled workspaceStrategy.provisionCommand Leading to OS Command ExecutionhighCVSS 8.8EPSS 0.8%
- Paperclip improper access control in codex_local inherits OpenAI Gmail connectorshighCVSS 8.7
- Paperclip arbitrary file read via adapterConfig in Claude adaptermediumCVSS 6.5
- Paperclip Stored XSS in MarkdownBody via URL transform bypassmediumCVSS 5.4
- Paperclip cross-tenant agent API key IDOR in /agents/:id/keyslowCVSS 3.1
- Paperclip stored XSS in MarkdownBody via javascript: URLslowCVSS 3.1
- Paperclip OS command injection in execution workspace cleanuplowCVSS 3.1
Vulnerabilities per week
The last 13 weeks, by the week each vulnerability was published.
| Week of | Bar | Vulns | Critical |
|---|---|---|---|
| 29 Jun 2026 | 0 | 0 | |
| 6 Jul 2026 | 0 | 0 | |
| 13 Jul 2026 | 0 | 0 | |
| 20 Jul 2026 | 0 | 0 | |
| 27 Jul 2026 | 0 | 0 | |
| 3 Aug 2026 | 0 | 0 | |
| 10 Aug 2026 | 0 | 0 | |
| 17 Aug 2026 | 1 | 1 | |
| 24 Aug 2026 | 0 | 0 | |
| 31 Aug 2026 | 0 | 0 | |
| 7 Sep 2026 | 0 | 0 | |
| 14 Sep 2026 | 0 | 0 | |
| 21 Sep 2026 | 0 | 0 |
How this is built
Junglewise Threat Intelligence collects vulnerabilities from NVD, GitHub Security Advisories, OSV, the CISA Known Exploited Vulnerabilities catalog, FIRST EPSS and vendor advisories, and matches each one to the technologies and vendors it affects. Dates are the date a vulnerability was published, in UTC.
The pages are rebuilt from the database every hour. Frozen weekly and monthly reports never change once published, so they can be cited.
Use this data
The same data is at https://junglewise.ai/threats/technologies/paperclip.json, for scripts and language models. It is free to reuse under CC BY 4.0 with a link back to this page.
Cite as: Junglewise Threat Intelligence, "Paperclip AI Paperclip vulnerabilities", https://junglewise.ai/threats/technologies/paperclip, 26 September 2026.