BB implementing-threat-modeling-with-mitre-attack
Implements threat modeling using the MITRE ATT&CK framework to map adversary TTPs against organizational assets, assess detection coverage gaps, and prioritize defensive investments. Use when SOC teams need to align detection engineering with threat landscape, conduct threat assessments for new environments, or justify security tool procurement.
Implements threat modeling using the MITRE ATT&CK framework to map adversary TTPs against organizational assets, assess detection coverage gaps, and…
As a process B 70/100 · Nearly there — weak spots: failures and branches, running it twice, progress reporting
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 · 5
✓ No critical or high findings
Medium and low: 5
-
low Risky intent
intent-offensive-securitySKILL.md:311Offensive-security / dual-use content (legitimate for authorised testing; review intended use)Test coverage using MITRE Caldera or Atomic Red Team:
-
low Risky intent
intent-offensive-securitySKILL.md:314Offensive-security / dual-use content (legitimate for authorised testing; review intended use)# Using Atomic Red Team to validate coverage for FIN7 techniques
-
low Risky intent
intent-offensive-securitySKILL.md:327Offensive-security / dual-use content (legitimate for authorised testing; review intended use)# T1003 — Credential Dumping
-
low Risky intent
intent-offensive-securitySKILL.md:351Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- **Atomic Red Team**: Open-source library of ATT&CK technique tests for security control validation
-
low Risky intent
intent-offensive-securitySKILL.md:384Offensive-security / dual-use content (legitimate for authorised testing; review intended use)Lateral Movement: 61% ███████░░░
Files scanned: 4. 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_ai_rmf" - note
frontmatter-keyunknown frontmatter key "atlas_techniques" - note
frontmatter-keyunknown frontmatter key "d3fend_techniques" - note
frontmatter-keyunknown frontmatter key "nist_csf" - note
frontmatter-keyunknown frontmatter key "mitre_attack"
Process rating: all ten parameters 70/100
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 3 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Tools and files. No external tools needed
- 100Steps. 20 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3114 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
- -41 reference files, but SKILL.md never points to them: the model will not open them
- -31 of 1 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 347: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 20 items
- +3Output format is stated explicitly
- +4Has examples (8 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.