DC configuring-windows-defender-advanced-settings
Configures Microsoft Defender for Endpoint (MDE) advanced protection settings including attack surface reduction rules, controlled folder access, network protection, and exploit protection. Use when hardening Windows endpoints beyond default Defender settings, deploying enterprise-grade endpoint protection, or meeting compliance requirements for advanced malware defense. Activates for requests involving Windows Defender configuration, ASR rules, MDE tuning, or Microsoft endpoint security.
Configures Microsoft Defender for Endpoint (MDE) advanced protection settings including attack surface reduction rules, controlled folder access, network…
As a process C 55/100 · Has gaps — weak spots: result and completion, failures and branches, running it twice
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 10
✓ No critical or high findings
Medium and low: 10
-
medium Dangerous commands
cmd-disable-securitySKILL.md:187Disables a security control (Defender, Gatekeeper, SIP, firewall, execution policy) (documentation of a security skill)Set-MpPreference -DisableBlockAtFirstSeen $false
security skill -
medium Dangerous commands
cmd-disable-securitySKILL.md:201Disables a security control (Defender, Gatekeeper, SIP, firewall, execution policy) (documentation of a security skill)Set-MpPreference -DisableRealtimeMonitoring $false
security skill -
medium Dangerous commands
cmd-disable-securitySKILL.md:202Disables a security control (Defender, Gatekeeper, SIP, firewall, execution policy) (documentation of a security skill)Set-MpPreference -DisableBehaviorMonitoring $false
security skill -
medium Dangerous commands
cmd-disable-securitySKILL.md:203Disables a security control (Defender, Gatekeeper, SIP, firewall, execution policy) (documentation of a security skill)Set-MpPreference -DisableIOAVProtection $false
security skill -
medium Dangerous commands
cmd-disable-securitySKILL.md:204Disables a security control (Defender, Gatekeeper, SIP, firewall, execution policy) (documentation of a security skill)Set-MpPreference -DisableScriptScanning $false
security skill -
low Risky intent
intent-offensive-securityreferences/standards.md:15Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)- Block credential stealing from LSASS → T1003.001 (OS Credential Dumping: LSASS)
detector -
low Risky intent
intent-offensive-securityreferences/standards.md:31Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| HIPAA | 164.308(a)(5)(ii)(B) - Malware protection | Defender AV + ransomware protection |
-
low Risky intent
intent-offensive-securitySKILL.md:42Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Enabling controlled folder access for ransomware protection
-
low Risky intent
intent-offensive-securitySKILL.md:115Offensive-security / dual-use content (legitimate for authorised testing; review intended use)### Step 2: Configure Controlled Folder Access (Ransomware Protection)
-
low Risky intent
intent-offensive-securitySKILL.md:272Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| **Controlled Folder Access** | Ransomware protection feature that prevents unauthorized applications from modifying files in protected folders |
Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "domain" - note
frontmatter-keyunknown frontmatter key "subdomain" - note
frontmatter-keyunknown frontmatter key "nist_csf" - note
frontmatter-keyunknown frontmatter key "mitre_attack"
Process rating: all ten parameters 55/100
- 0Result and completion. Does not say what the result is
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 6 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 20 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2834 tokens
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +3Output format is not stated: the model decides each time
- -43 reference files, but SKILL.md never points to them: the model will not open them
- -32 of 2 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 493: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 20 items
- +4Has examples (8 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.