awesome-game-security is a curated collection focused on security research for games and game software, including cheating, anti-cheat systems, debugging, and anti-debugging. It is intended for security researchers and developers studying or building game-protection tools. The catalogue entries provide skills for AI coding agents related to the repository’s security workflows.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add gmh5225/awesome-game-security --skill dma-attackgit clone --depth 1 https://github.com/gmh5225/awesome-game-securityWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/gmh5225/awesome-game-security/dma-attack)<a href="https://agentmods.dev/skills/gmh5225/awesome-game-security/dma-attack"><img src="https://agentmods.dev/badge/skills/gmh5225/awesome-game-security/dma-attack/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/gmh5225/awesome-game-security/dma-attack"><img src="https://agentmods.dev/badge/skills/gmh5225/awesome-game-security/dma-attack.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 1162 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00045 | $0.00347 |
| Opus 5.5 | $0.00018 | $0.00139 |
| Sonnet 5.5 | $0.00009 | $0.00069 |
| Haiku 4.5 | $0.00005 | $0.00035 |
Grade A, and why
dma-attack-techniques scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
DMA attack techniques
Identify the memory initiator, transport, required privilege, isolation boundary, and observable artifacts before classifying a technique as DMA.
Topic routing
- Classification and threat model for acquisition-path distinctions and attacker prerequisites.
- PCIe devices for TLPs, configuration space, programmable endpoints, and emulation limits.
- IOMMU and defense for VT-d/AMD-Vi, ACS, ATS/PASID, domain assignment, hypervisors, and trust anchors.
- IOMMU state verification for separating ACPI advertisement, Windows policy, live unit state, and per-requester coverage.
- Detection and forensics for defensive PCIe inventory, signal correlation, evidence capture, Thunderbolt/USB4, and memory access.
- Acquisition and transport, assurance boundaries, and repository resources for focused evidence and source selection.
- Repository map when maintaining the collection.
Use windows-kernel-security for host driver and kernel internals. Apply game-security-research-rigor before turning architecture claims into findings.
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/acquisition-and-transport.md 7.0 KB
- references/assurance-boundaries.md 6.3 KB
- references/classification-and-threat-model.md 3.8 KB
- references/detection-and-forensics.md 18 KB
- references/iommu-and-defense.md 26 KB
- references/iommu-state-verification.md 13 KB
- references/pcie-devices.md 24 KB
- references/repository-map.md 4.6 KB
- references/repository-resources.md 4.4 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago Changed · +1 lines b6664c9e1bea
- 1mo ago Changed · -1,648 lines · -59 tokens per session 53f9a6f1794c
- 1mo ago Changed · -114 lines · +34 tokens per session 37e884f7def0
- 1mo ago First seen · 1,782 lines · 70 tokens per session scan A 4c6f8ee00a51
dma-attack-techniques is a skill published in the GitHub repository gmh5225/awesome-game-security (3,656 stars, last pushed yesterday), licensed MIT. It adds 45 tokens to every session and 347 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
inspect-computer-config
Use when the user asks to inspect, summarize, audit, compare, or troubleshoot this computer's hardware, operating system, CPU, memory, GPU, disk, or local runtime configuration.
openhue
Control Philips Hue lights via OpenHue CLI + Hue Bridge API.
bolt-iot-automation
Automate Bolt Iot tasks via Rube MCP (Composio). Always search tools first for current schemas.
eartrumpet
Inspect and route per-application audio with EarTrumpet, WASAPI, and pycaw; troubleshoot audio sessions and output devices.
integrations
NextDNS integration guides for third-party platforms and services. This skill should be used when integrating NextDNS with routers, home automation systems, network management platforms, or other third-party services. It also guides transport selection across DoH, DoT, DoQ, DoH3, IPv6, and legacy DNS. Triggers on…
external-gitcode-ascend-atb-debug-guide
A troubleshooting guide for ATB operator tests and Ascend NPU environments. It covers issues such as ABI mismatches, memory errors, failed CSV tests, and ACLNN interface problems.