Cold Coffee Game Security
SkillDocs & knowledge全局自动路由 | Defensive game security and cheat research covering external and internal cheat architecture, trainers, memory tampering, ESP/overlay, aim automation, injection and hooks, packet manipulation, anti-cheat telemetry, integrity, Unity IL2CPP, Unreal, incident analysis, and detection validation.
Available today. Use it from your connected AI after setup.
No other account needed.
Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.
Then ask your AI: use the Cold Coffee Game Security skill
What this skill tells your AI
The instructions your AI receives, as published by alicewe1/alice_skill in _modules/eni-game-security/SKILL.md and read by ahel’s review.
Analyze the abuse path from trust boundary to observable behavior, then implement detection and hardening.
Start
- Identify engine, platform, architecture, network model, authoritative state, anti-cheat components, and available artifacts.
- Classify the technique: external memory, injected/internal, input automation, overlay/ESP, runtime patch, packet/protocol, asset/config, kernel/driver, DMA/hardware, or account/economy abuse.
- Map required access, modified state, data sources, persistence/lifecycle, and observable artifacts.
- Reproduce only the minimum behavior needed to validate detection or a defensive hypothesis.
Select references
- Cheat categories, data flows, and observables: read
references/cheat-architecture.md. - Anti-cheat architecture and control placement: read
references/anti-cheat-design.md. - Unity/IL2CPP and Unreal analysis: read
references/engine-security.md. - Investigation and evidence: read
references/incident-analysis.md.
Tools
- Use
scripts/integrity_manifest.pyto create or verify signed-off file hash manifests. - Use
scripts/telemetry_analyze.pyto summarize player/input telemetry and flag explainable anomaly indicators. - Combine with
$eni-reverse-deep,$eni-memory-forensics, and$eni-case-labfor binaries, runtime state, and evidence handling.
Deliver
Return the technique classification, trust-boundary failure, required capabilities, observables, reproduction harness, integrity/telemetry checks, false-positive considerations, mitigations, and retest plan. Separate a detection hypothesis from a confirmed cheat artifact.
Signals
- GitHub stars
- 26
- Forks
- 4
- Last commit
- Sep 2026
Advanced
- Item type
- skill
- Key
eni-game-security- Source
- github.com/alicewe1/alice_skill