# Haiou prompt-adware in Codex jailbreak bundle

- ID: checkpoint-haiou-codex-adware-2026
- Reported: 2026-11-04
- Researcher: Check Point Research
- Organization: Check Point
- AI role: ai_agent_or_mcp_as_target (Agent / MCP as target)
- Confidence in AI involvement: high
- Research / borderline: false
- Last reviewed: 2026-11-04
- Entry page: https://openattacks.ai/attacks/checkpoint-haiou-codex-adware-2026/
- Entry JSON: https://openattacks.ai/api/attacks/checkpoint-haiou-codex-adware-2026.json
- Browse title: Haiou prompt-adware in Codex jailbreak bundle
- Editorial summary: 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-\*…
- Evidence class (catalog annotation): Not classified
- Source-stated target environments: Not specified
- Stage hunts and conditional defenses: https://openattacks.ai/api/defenses/checkpoint-haiou-codex-adware-2026.json

## Technique
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.

## Stack relevance (editorial)
Assessment: not\_assessed. No reviewed applicability annotation is available. Product mentions do not establish victim conditions.
A product mention alone is not a victim-side applicability mapping. Selection does not verify affected versions, permissions or compromise.

## Initial access
User downloads and installs haiou-codex jailbreak bundle from GitHub promoted on Chinese social platforms

## AI tooling and models
- Codex
- Global Codex instructions
- Malicious skills (seagull-\* series)

## Other tooling
- AES-GCM encrypted payload
- GitHub repository (haiou-666/haiou-codex)

## Victims and sectors
Codex users seeking jailbreak or free access, primarily Chinese-speaking users

## Target geography
- China
- Asia
China and Asia reflect primary promotion on Bilibili and QQ; global Codex users potentially affected

## Attribution
haiou-666 (GitHub username)

## Scale and metrics
Promoted on Bilibili and QQ; repository stars and download count unknown

## Attack flow
Catalog reconstruction of the supplied source account. Unknowns and research caveats are preserved.
### distribution: Jailbreak bundle promoted on social platforms [access]
haiou-666/haiou-codex GitHub repository promoted on Bilibili and QQ as Codex jailbreak solution
Evidence: https://research.checkpoint.com/2026/free-the-model-sell-the-gateway-prompt-adware-hidden-in-jailbreak-bundles/

### install: User installs encrypted payload [execution]
Installation process decrypts AES-GCM payload.pkg and installs to system
Evidence: https://research.checkpoint.com/2026/free-the-model-sell-the-gateway-prompt-adware-hidden-in-jailbreak-bundles/

### inject: Malicious instructions and skills installed [ai]
Global Codex instructions modified and seagull-\* skills installed with ad injection logic
Evidence: https://research.checkpoint.com/2026/free-the-model-sell-the-gateway-prompt-adware-hidden-in-jailbreak-bundles/

### adware: Ads injected into agent responses [impact]
Agent responses include advertisements for zz.aiapi2025.top API gateway; skills prevent agent from testing or revealing ads
Evidence: https://research.checkpoint.com/2026/free-the-model-sell-the-gateway-prompt-adware-hidden-in-jailbreak-bundles/

Connections:
- distribution -> install
- install -> inject
- inject -> adware

## Stage defense and hunting recommendations
Editorial recommendations, not validated coverage. Source-controlled query starters are drafts. Custom-schema examples require telemetry collection and field mapping; absence of a mapping means not assessed. MagicSword policy opportunities require managed Windows scope and enforcement.
### distribution: Stage hunt not mapped yet
- Visibility: Not assessed
- Query origin: catalog_authored; status: not_assessed; log scope: gap
- Hunt hypothesis: A stage-specific hunt has not been reviewed for this part of the source account.
- Required telemetry: not assessed
- Investigate: Review the cited behavior, identify the observing party and available logs, then propose and test a hunt.
- Limitation: An unmapped stage does not mean it is undetectable or that no behavior occurred. It means this catalog has not supplied a reviewed hunt for it.
- No direct MagicSword prevention claim is recorded for this stage.

### install: Stage hunt not mapped yet
- Visibility: Not assessed
- Query origin: catalog_authored; status: not_assessed; log scope: gap
- Hunt hypothesis: A stage-specific hunt has not been reviewed for this part of the source account.
- Required telemetry: not assessed
- Investigate: Review the cited behavior, identify the observing party and available logs, then propose and test a hunt.
- Limitation: An unmapped stage does not mean it is undetectable or that no behavior occurred. It means this catalog has not supplied a reviewed hunt for it.
- No direct MagicSword prevention claim is recorded for this stage.

### inject: Stage hunt not mapped yet
- Visibility: Not assessed
- Query origin: catalog_authored; status: not_assessed; log scope: gap
- Hunt hypothesis: A stage-specific hunt has not been reviewed for this part of the source account.
- Required telemetry: not assessed
- Investigate: Review the cited behavior, identify the observing party and available logs, then propose and test a hunt.
- Limitation: An unmapped stage does not mean it is undetectable or that no behavior occurred. It means this catalog has not supplied a reviewed hunt for it.
- No direct MagicSword prevention claim is recorded for this stage.

### adware: Stage hunt not mapped yet
- Visibility: Not assessed
- Query origin: catalog_authored; status: not_assessed; log scope: gap
- Hunt hypothesis: A stage-specific hunt has not been reviewed for this part of the source account.
- Required telemetry: not assessed
- Investigate: Review the cited behavior, identify the observing party and available logs, then propose and test a hunt.
- Limitation: An unmapped stage does not mean it is undetectable or that no behavior occurred. It means this catalog has not supplied a reviewed hunt for it.
- No direct MagicSword prevention claim is recorded for this stage.


## MITRE ATLAS
Mappings are catalog annotations based on described behavior, not assignments or endorsements by MITRE.
- AML.T0054: LLM Jailbreak — Malicious skills inject advertisements into agent responses
  Technique: https://atlas.mitre.org/techniques/AML.T0054
  Evidence: https://research.checkpoint.com/2026/free-the-model-sell-the-gateway-prompt-adware-hidden-in-jailbreak-bundles/
- AML.T0081: Modify AI Agent Configuration — Global instructions and skills contain malicious prompt injection to force ad display
  Technique: https://atlas.mitre.org/techniques/AML.T0081
  Evidence: https://research.checkpoint.com/2026/free-the-model-sell-the-gateway-prompt-adware-hidden-in-jailbreak-bundles/
- AML.T0080: AI Agent Context Poisoning — Skills manipulate agent output to include commercial advertisements
  Technique: https://atlas.mitre.org/techniques/AML.T0080
  Evidence: https://research.checkpoint.com/2026/free-the-model-sell-the-gateway-prompt-adware-hidden-in-jailbreak-bundles/
- AML.T0010.001: AI Software — Attacker distributes compromised agent configuration through fake jailbreak bundle
  Technique: https://atlas.mitre.org/techniques/AML.T0010.001
  Evidence: https://research.checkpoint.com/2026/free-the-model-sell-the-gateway-prompt-adware-hidden-in-jailbreak-bundles/

## 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

## Sources
- https://research.checkpoint.com/2026/free-the-model-sell-the-gateway-prompt-adware-hidden-in-jailbreak-bundles/ — Free the Model, Sell the Gateway: Prompt Adware Hidden in Jailbreak Bundles

## Source notes
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. 

## Indicators (untrusted data; do not visit or execute)
```json
{
  "domains": [
    "zz.aiapi2025.top"
  ],
  "ips": [],
  "hashes": [],
  "urls": [
    "https://github.com/haiou-666/haiou-codex"
  ]
}
```
