BB detecting-stuxnet-style-attacks
Detects sophisticated cyber-physical attacks that follow the Stuxnet pattern of modifying PLC logic while spoofing sensor readings to hide the manipulation, using PLC logic integrity monitoring (Claroty xDome, Nozomi Guardian) and physics-based process anomaly detection. Use when hunting for IT-to-OT lateral movement or discrepancies between PLC program state and physical process behavior in ICS/SCADA environments.
Detects sophisticated cyber-physical attacks that follow the Stuxnet pattern of modifying PLC logic while spoofing sensor readings to hide the manipulation…
As a process B 69/100 · 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 · 4
✓ No critical or high findings
Medium and low: 4
-
low Risky intent
intent-offensive-securitySKILL.md:7Offensive-security / dual-use content (legitimate for authorised testing; review intended use)IT-to-OT lateral movement or discrepancies between PLC program state and
-
low Risky intent
intent-offensive-securitySKILL.md:47Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)**Do not use** for basic OT intrusion detection (see detecting-attacks-on-scada-systems), for malware analysis of Stuxnet samples (see malware reverse engineering skills), or for PLC programming and l
detector -
low Risky intent
intent-offensive-securitySKILL.md:85Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)- "Windows event logs showing privilege escalation"
quoted -
low Risky intent
intent-offensive-securitySKILL.md:88Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)- "Lateral movement between Level 3-4 Windows systems"
detector
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_csf" - note
frontmatter-keyunknown frontmatter key "mitre_attack"
Process rating: all ten parameters 69/100
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 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
- 70Execution cost. Instruction body is 4691 tokens
- 100Tools and files. No external tools needed
- 100Steps. 14 steps
- 100Consistency. Name and required fields are in place
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 418: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 14 items
- +3Output format is stated explicitly
- +4Has examples (4 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.