Is there a public exploit for CVE-2026-107685?

No public exploit for CVE-2026-107685 was found in Exploit-DB, Metasploit, Nuclei templates or public proof-of-concept repositories. That is an absence of evidence rather than proof that none exists.

How severe is CVE-2026-107685?

CVE-2026-107685 scores CVSS 9.1 (v4.0), rated critical. EPSS puts the chance of exploitation in the next 30 days at 0.27%.

What does CVE-2026-107685 affect?

CVE-2026-107685 affects agentjido req_llm.

9.1 Critical

Improper Certificate Validation vulnerability in the WebSocket streaming client in agentjido reqllm allows an on-path attacker to read and…

CVE-2026-107685

Improper Certificate Validation vulnerability in the WebSocket streaming client in agentjido reqllm allows an on-path attacker to read and modify OpenAI WebSocket sessions, including the authorization bearer token, via a TLS certificate the client does not trust. ReqLLM.Streaming.WebSocketSession.Client.start/3 in lib/reqllm/streaming/websocketsession/client.ex starts WebSockex without TLS options, and WebSockex defaults to insecure: true, which connects with verify: :verifynone. The option allowlist also drops any caller-supplied cacerts or ssloptions, so an application cannot turn verification on. The OpenAI Responses, Realtime, and Codex WebSocket paths reach this client and send the API key or OAuth access token in the authorization header. HTTP streaming through Finch and the HTTP/2 duplex session through Mint verify certificates and are not affected. This issue affects reqllm: from 1.9.0 before 1.29.0.

Assessment

CVSS: 9.1 (v4.0)
Severity: Critical
EPSS: 0.27% chance of exploitation in the next 30 days
Known exploited: Not listed in CISA KEV
Exploit availability: Nothing found in Exploit-DB, Metasploit, Nuclei or public PoC repositories
Published: 23 October 2026
Last updated: 2 November 2026
Affected: agentjido · req_llm
Assigner: EEF

CVSS vectorCVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:H/VI:H/VA:N/SC:N/SI:N/SA:N

At the source

EUVD (ENISA)

References

Community proofs of concept

No community proof of concept yet. If you have one for a published vulnerability and the right to share it, add it below — it will appear here once reviewed.

Submit a proof of concept

Only for publicly disclosed vulnerabilities, and only material from testing you were authorised to perform. This platform does not buy, sell, or broker exploits — see earning from vulnerability research for legitimate bounty programs. Submissions are reviewed before they appear. Text only; do not include live credentials, personal data, or anything targeting systems you are not permitted to test.

Title *

Proof of concept *

Write-up (optional)

Affected versions (optional)

Name or handle (optional)

References (optional, one URL per line)

Licence for your contribution *

Private contact (optional, never shown)

Before you submit * This vulnerability is already publicly disclosed (it has a published CVE). This material comes only from testing I was authorised to perform. I have the legal right to publish this content and am not breaching any agreement by doing so. It contains no live credentials, personal data, or anything targeting systems I am not authorised to test. I understand it will be reviewed before it appears publicly and may be rejected. I agree to the submission terms.

What is 5 + 2? *

Query this programmatically

Agents can read this through the MCP endpoint, or over HTTP:

curl https://cve.zerocrew.in/api/cve/CVE-2026-107685