CC detecting-credential-dumping-techniques
Detect LSASS credential dumping, SAM database extraction, and NTDS.dit theft (e.g. via Mimikatz) using Sysmon Event ID 10 process-access logging, Windows Security logs, and SIEM correlation rules. Use when hunting for credential-theft activity on Windows/Active Directory hosts or triaging EDR alerts on LSASS access.
Detect LSASS credential dumping, SAM database extraction, and NTDS.dit theft (e.g. via Mimikatz) using Sysmon Event ID 10 process-access logging, Windows…
As a process C 53/100 · Has gaps — weak spots: result and completion, when it triggers, failures and branches
How to improve
For the model run — optional
- 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 · 7
✓ No critical or high findings
Medium and low: 7
-
low Risky intent
intent-offensive-securityreferences/api-reference.md:1Offensive-security / dual-use content (legitimate for authorised testing; review intended use)# Credential Dumping Detection API Reference
-
low Risky intent
intent-offensive-securitySKILL.es.md:3Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)description: Detect LSASS credential dumping, SAM database extraction, and NTDS.dit theft using Sysmon Event ID 10, Windows Security logs, and SIEM correlation rules
detector -
low Risky intent
intent-offensive-securitySKILL.md:3Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)description: Detect LSASS credential dumping, SAM database extraction, and NTDS.dit theft (e.g. via Mimikatz) using Sysmon Event ID 10 process-access logging, Windows Security logs, and SIEM correlati
detector -
low Risky intent
intent-offensive-securitySKILL.md:63Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)# Detecting Credential Dumping Techniques
detector -
low Risky intent
intent-offensive-securitySKILL.md:67Offensive-security / dual-use content (legitimate for authorised testing; review intended use)Credential dumping (MITRE ATT&CK T1003) is a post-exploitation technique where adversaries extract authentication credentials from OS memory, registry hives, or domain controller databases. This skill
-
low Risky intent
intent-offensive-securitySKILL.md:72Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)- When investigating security incidents that require detecting credential dumping techniques
detector -
low Risky intent
intent-offensive-securitySKILL.md:96Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)JSON report containing detected credential dumping indicators with technique classification, severity ratings, process details, MITRE ATT&CK mapping, and Splunk/Elastic detection queries.
detector
Files scanned: 5. 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 "d3fend_techniques" - note
frontmatter-keyunknown frontmatter key "nist_csf" - note
frontmatter-keyunknown frontmatter key "mitre_attack" - note
frontmatter-keyunknown frontmatter key "mitre_f3"
Process rating: all ten parameters 53/100
- 0Result and completion. Does not say what the result is
- 0Failures and branches. Linear process with no failure handling
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 2 mutating operations with no state check
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 15 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 469 tokens
- 100Progress reporting. Reports progress
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- -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
- +3Description length 317: enough signal without eating the budget
- +4Structure: 6 headings
- +3Step-by-step instructions: 15 items
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 71.