VULNpocalypse

CVE-2026-115727: AgenticSeek before commit 409840c RCE via Exposed Werkzeug Debugger in llm_server

Advisory generated from the CVE record, CISA, Exploit Observer and VEDAS: what it is, whether it is exploited, who is affected, and how to fix and detect it.

Generated by VEDAS. Scores as of 2026-11-11 15:49 UTC. Rebuilt every few hours from cve-scores, CISA KEV and vedas-signatures. How this works and its limits.

What it is

AgenticSeek before commit 409840c contains a remote code execution vulnerability because llm_server/app.py hardcodes Flask debug mode while binding to all interfaces. Attackers who reach the server port and obtain the derivable Werkzeug debugger PIN can execute Python code and operating system commands with llm_server privileges.

Description quoted from the CVE record (assigned by VulnCheck, published 2026-10-23).

Weakness: Active Debug Code

How it can be exploited

Exploitable over the network with low attack complexity only when specific conditions are present needing no privileges and no user interaction. Impact: confidentiality high, integrity high, availability high. CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N

CISA assessment (SSVC): CISA has no evidence of exploitation. Automatable: no. Technical impact: total.

Public exploit evidence (Exploit Observer)

Exploit Observer found 5 code repositories naming this CVE.

Code repositories that name a CVE are often scanners, copies or fakes, and some are malware. Read the code before running anything.

See all 7 references on Exploit Observer

Live scores

EPSS
0.007
low predicted chance of attack
VEDAS
0.986
strong exploit evidence
On CISA KEV
Not listed
Detection rule
Nuclei · Suricata

Who is affected

ProductAffectedNot affected
Fosowl AgenticSeekbefore 409840c03385 (git commit)Not stated

Version ranges exactly as the CVE record states them. “Before X” means X is the first fixed version.

How to fix it

Vendor guidance:

How to detect it

Nuclei template (active check)

AgenticSeek llm_server - Exposed Werkzeug Debugger (Flask Debug Mode)

AgenticSeek before commit 409840c starts its llm_server Flask application (llm_server/app.py) with debug mode enabled while binding to all interfaces (host 0.0.0.0). The Werkzeug interactive debugger is therefore reachable by anyone who can connect to the server port, and once the derivable debugger PIN is recovered an attacker can execute arbitrary Python and operating-system commands as the llm_server process. This template confirms the interactive debugger middleware is active by requesting a Werkzeug debugger static resource (served by DebuggedApplication only when debug mode is enabled) and matching the debugger JavaScript, without attempting any code execution.

Name and description quoted from the template, written by VEDAS.

The template sends 1 request (GET /?__debugger__=yes&cmd=resource&f=debugger.js); it decides using status, word matchers. Severity in the template: critical. Marked as not yet verified against a live vulnerable target.

Run it against a host you own or are authorised to test:

bash
nuclei -u https://your-host -t CVE-2026-115727.yaml
Show the template (45 lines)
yaml
id: CVE-2026-115727

info:
  name: "AgenticSeek llm_server - Exposed Werkzeug Debugger (Flask Debug Mode)"
  author: vedas-arpsyndicate
  severity: critical
  description: |
    AgenticSeek before commit 409840c starts its llm_server Flask application (llm_server/app.py)
    with debug mode enabled while binding to all interfaces (host 0.0.0.0). The Werkzeug interactive
    debugger is therefore reachable by anyone who can connect to the server port, and once the
    derivable debugger PIN is recovered an attacker can execute arbitrary Python and operating-system
    commands as the llm_server process. This template confirms the interactive debugger middleware is
    active by requesting a Werkzeug debugger static resource (served by DebuggedApplication only when
    debug mode is enabled) and matching the debugger JavaScript, without attempting any code execution.
  reference:
    - https://www.exploit.observer/?keyword=CVE-2026-115727&match=exact
    - https://subdomain.center/?engine=ammonites&keyword=agenticseek&match=exact
  classification:
    cvss-metrics: CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H
    cve-id: CVE-2026-115727
    cwe-id: CWE-489
  metadata:
    verified: false
  tags: cve,cve2026,agenticseek,werkzeug,flask,debug,exposure
http:
  - raw:
      - |
        GET /?__debugger__=yes&cmd=resource&f=debugger.js HTTP/1.1
        Host: {{Hostname}}

    matchers-condition: and
    matchers:
      - type: status
        status:
          - 200
      - type: word
        part: header
        words:
          - "javascript"
      - type: word
        part: body
        condition: and
        words:
          - "CONSOLE_MODE"
          - "initPinBox"

CVE-2026-115727.yaml on GitHub

Suricata rules (network detection)

1 rule that alert on traffic matching this exploit: VEDAS CVE-2026-115727 AgenticSeek llm_server Exposed Werkzeug Debugger Resource Access. Add them to your Suricata rule set and reload.

Show the rules
suricata
alert http $EXTERNAL_NET any -> $HTTP_SERVERS $HTTP_PORTS (msg:"VEDAS CVE-2026-115727 AgenticSeek llm_server Exposed Werkzeug Debugger Resource Access"; flow:established,to_server; http.uri; content:"__debugger__=yes"; fast_pattern; nocase; content:"cmd=resource"; nocase; distance:0; classtype:web-application-attack; reference:cve,CVE-2026-115727; reference:url,https://www.exploit.observer/?keyword=CVE-2026-115727&match=exact; reference:url,https://subdomain.center/?engine=ammonites&keyword=agenticseek&match=exact; sid:1082800; rev:1;)

CVE-2026-115727.rules on GitHub

References

Vendor advisories and patches

Technical analysis and advisories

Other databases

Where this comes from

This advisory is generated automatically by VEDAS from: CVE.org record, cve-scores (EPSS and VEDAS), Exploit Observer, vedas-signatures. Text in quotes is reproduced from the source; everything else is a fixed template filled with source fields. Nothing here is written by a language model. Check the vendor advisory before acting, and read how VEDAS and Exploit Observer work, and their limits.

Supporting partners

Feasible SecurityAskealGoTrust