windows-kernel-security
Guide for Windows kernel internals and security mechanisms used in game protection and low-level research. Use this skill when working with drivers, IRQL-sensitive callbacks, EPROCESS, ETHREAD, MMVAD internals, IOCTL paths, DSE, PatchGuard, HVCI, PiDDBCache, MmUnloadedDrivers, or kernel memory inspection.
63
75%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Critical
Do not install without reviewing
Fix and improve this skill with Tessl
tessl review fix ./.claude/skills/windows-kernel/SKILL.mdSecurity
3 findings: 2 critical severity, 1 medium severity. Installing this skill is not recommended: please review these findings carefully if you do intend to do so.
E005: Suspicious download URL detected in skill instructions.
What this means
Detected a suspicious URL in the skill instructions that could lead the agent to download and execute malicious scripts or binaries. This includes links to executables from untrusted sources, typosquatting of official packages, URL shorteners that obscure the destination, and personal file hosting services.
Why it was flagged
The raw.githubusercontent.com links point to a personal/unknown GitHub repository (gmh5225) hosting archived code and autogenerated descriptions for many game-security/cheat projects (some of which are dual-use or can include binaries), making them an untrusted distribution channel that could be used to host malware; the Microsoft symbol server (msdl.microsoft.com) is legitimate and not suspicious.
E006: Malicious code pattern detected in skill scripts.
What this means
Detected high-risk code patterns in the skill content — including its prompts, tool definitions, and resources — such as data exfiltration, backdoors, remote code execution, credential theft, system compromise, supply chain attacks, and obfuscation techniques.
Why it was flagged
The README contains step-by-step exploit workflows (loading vulnerable signed drivers, achieving kernel R/W, disabling DSE, executing arbitrary kernel code), persistence techniques (EFI bootkits, boot-time injection), and stealth/tampering instructions (ETW/telemetry patching, PiDDB/MmUnloadedDrivers manipulation, callback/list patching) that directly enable kernel-level compromise, persistence and evasion—indicating clearly malicious/abusive intent and high risk.
W013: Attempt to modify system services in skill instructions.
What this means
The skill prompts the agent to compromise the security or integrity of the user’s machine by modifying system-level services or configurations, such as obtaining elevated privileges, altering startup scripts, or changing system-wide settings.
Why it was flagged
The skill contains explicit instructions for loading/unloading drivers, disabling Driver Signature Enforcement, bypassing PatchGuard/ETW, and performing kernel memory/physical memory operations—actions that require elevated privileges and directly modify the machine's state.
Low
Low-risk findings.
2 low severity findings. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
The required workflow explicitly fetches and ingests public web content at runtime from `raw.githubusercontent.com` (outsider-authored README/archive/description files), which can include free-form text that the agent will add to its LLM context.
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
The skill explicitly instructs the agent to fetch and use external raw GitHub content at runtime (e.g., https://raw.githubusercontent.com/gmh5225/awesome-game-security/refs/heads/main/README.md), which will directly be injected into the agent's context and therefore can control prompts/output.
- Repository
- gmh5225/awesome-game-security
- Commit
9efdfd0
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.