Not classified

Haiou prompt-adware in Codex jailbreak bundle

GitHub repository haiou-666/haiou-codex promoted on Bilibili and QQ as Codex jailbreak bundle. Installation decrypts AES-GCM encrypted payload.pkg and installs global Codex instructions plus seagull-*…

What happened

GitHub repository haiou-666/haiou-codex promoted on Bilibili and QQ as Codex jailbreak bundle. Installation decrypts AES-GCM encrypted payload.pkg and installs global Codex instructions plus seagull-* skills that inject advertisements for zz.aiapi2025.top into agent responses. Malicious skills also prevent agent from testing or revealing the injected ads. Attack monetizes jailbreak distribution through forced API gateway advertising while appearing to provide free model access workarounds.

Read the original source

How it happened

Select a stage to explore its defenses
Select a stage · Drag to explore · + / − to zoom · Dashed edges are loopsSelect a stage · Arrows show reported connectionsReported sequence
Read the flow as text & sources

A catalog reconstruction of the supplied source account. Unknown steps remain explicit; an edge describes the reported relationship between steps.

  1. 01 · Jailbreak bundle promoted on social platforms

    haiou-666/haiou-codex GitHub repository promoted on Bilibili and QQ as Codex jailbreak solution

    Source for step 1
  2. 02 · User installs encrypted payload

    Installation process decrypts AES-GCM payload.pkg and installs to system

    Source for step 2
  3. 03 · Malicious instructions and skills installed

    Global Codex instructions modified and seagull-* skills installed with ad injection logic

    Source for step 3
  4. 04 · Ads injected into agent responses

    Agent responses include advertisements for zz.aiapi2025.top API gateway; skills prevent agent from testing or revealing ads

    Source for step 4

Why it matters

Reported entry point: User downloads and installs haiou-codex jailbreak bundle from GitHub promoted on Chinese social platforms. Reported impact: Agent responses include advertisements for zz.aiapi2025.top API gateway; skills prevent agent from testing or revealing ads; reported targets include Codex users seeking jailbreak or free access, primarily Chinese-speaking users; applicability to your setup has not been assessed, so verify affected versions, permissions, and configuration in the original report.

Read the original report

What you can do

Protection & prevention

Review global Codex instructions for unauthorized modifications; scan installed skills for ad injection patterns; monitor agent responses for unexpected commercial content; verify instruction and skill sources; detect connections to suspicious API gateways; educate users about jailbreak bundle risks

Catalog defensive guidance based on the reported behavior. Confirm scope and current mitigations in the original source.

Review the original guidance
Technical detailsTooling, impact & MITRE ATLAS

Attack context

AI's role
Agent / MCP as target
Initial access
User downloads and installs haiou-codex jailbreak bundle from GitHub promoted on Chinese social platforms

Tooling as reported

AI products, models and artifacts

  • Codex
  • Global Codex instructions
  • Malicious skills (seagull-* series)

Other tooling

  • AES-GCM encrypted payload
  • GitHub repository (haiou-666/haiou-codex)

Targets and reported impact

Targets / sectors
Codex users seeking jailbreak or free access, primarily Chinese-speaking users
Reported scale / exposure
Promoted on Bilibili and QQ; repository stars and download count unknown
Target geography
China · Asia

China and Asia reflect primary promotion on Bilibili and QQ; global Codex users potentially affected

Reported attribution

haiou-666 (GitHub username)

Source defensive notes

Review global Codex instructions for unauthorized modifications; scan installed skills for ad injection patterns; monitor agent responses for unexpected commercial content; verify instruction and skill sources; detect connections to suspicious API gateways; educate users about jailbreak bundle risks

MITRE ATLAS

AI-specific catalog annotations based on the reported behavior; these are not MITRE case-study assignments.

AML.T0054LLM Jailbreak

Malicious skills inject advertisements into agent responses Source

AML.T0081Modify AI Agent Configuration

Global instructions and skills contain malicious prompt injection to force ad display Source

AML.T0080AI Agent Context Poisoning

Skills manipulate agent output to include commercial advertisements Source

AML.T0010.001AI Software

Attacker distributes compromised agent configuration through fake jailbreak bundle Source

Indicators of compromise

domains

  • zz.aiapi2025.top

ips

    hashes

      urls

      • https://github.com/haiou-666/haiou-codex

      Sources & research credit

      1 source

      Research by Check Point Research · Check Point

      1. Free the Model, Sell the Gateway: Prompt Adware Hidden in Jailbreak Bundles research.checkpoint.com

      Relevant detection rules: - Monitor modifications to global Codex instructions - Detect installation of unexpected skills (seagull-* naming pattern) - Alert on connections to suspicious API gateways (zz.aiapi2025.top) - Review skill content for ad injection patterns or output manipulation logic - Note: No direct Sigma rules for agent skill poisoning; requires custom monitoring of agent configuration changes and skill installation events, plus network monitoring for unexpected API gateway connections.

      Record & downloads
      Source record name
      Haiou prompt-adware in Codex jailbreak bundle
      Entry ID
      checkpoint-haiou-codex-adware-2026
      Catalog review
      November 4, 2026
      AI-role confidence
      high