SKILLEMALL.ai
GitHub ↗ RU Sign in

CB detecting-t1003-credential-dumping-with-edr

Detect OS credential dumping (MITRE T1003) targeting LSASS memory, the SAM database, NTDS.dit, and cached credentials by correlating EDR telemetry, Sysmon process-access events, and Windows security event logs. Use when hunting for Mimikatz-style credential theft, triaging an EDR alert on LSASS access, or scoping an incident after suspected credential dumping.

mukul975/Anthropic-Cybersecurity-Skills Agent Skills author: mukul975 Apache-2.0 8 files · 2 scripts body ≈ 1 433 tokens Open the sourcegithub.com↗ analyzed 6 d ago

Detect OS credential dumping (MITRE T1003) targeting LSASS memory, the SAM database, NTDS.dit, and cached credentials by correlating EDR telemetry, Sysmon…

As a process B 67/100 · Nearly there — weak spots: when it triggers, failures and branches, running it twice

AnalyzerPeople and hiringData and analyticstype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
C
81/100
safety, quality, tests
Safety 60%
83
Quality 40%
78
Run on models
none yet
Process rating
B
67/100
Nearly there
Failures and branches w 10
0
Progress reporting w 2
0
When it triggers w 12
20
the three weakest of ten parameters · all ten

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 · 17

    ✓ No critical or high findings

    Medium and low: 17
    • low Risky intent intent-offensive-security assets/template.md:1
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      # T1003 Credential Dumping Hunt Template
    • low Risky intent intent-offensive-security assets/template.md:12
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      > An adversary with elevated privileges is dumping credentials from LSASS memory, SAM database, or NTDS.dit to enable lateral movement and privilege escalation.
    • low Risky intent intent-offensive-security assets/template.md:36
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      3. **Investigate**: [Lateral movement from compromised credentials]
    • low Risky intent intent-offensive-security references/api-reference.md:1
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      # API Reference: T1003 Credential Dumping Detection
    • low Risky intent intent-offensive-security references/api-reference.md:14
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      ## Sysmon Events for Credential Dumping
    • low Risky intent intent-offensive-security references/standards.md:1
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      # Standards and References - T1003 Credential Dumping Detection
    • low Risky intent intent-offensive-security references/standards.md:3
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      ## MITRE ATT&CK Credential Dumping Sub-Techniques
    • low Risky intent intent-offensive-security references/standards.md:14
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      ## LSASS Access Masks for Credential Dumping
    • low Risky intent intent-offensive-security references/standards.md:35
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      ## Known Credential Dumping Tools
    • low Risky intent intent-offensive-security references/standards.md:45
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
      | LaZagne | Multi-source credential harvesting | lazagne.exe all |
      detector
    • low Risky intent intent-offensive-security references/workflows.md:1
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      # Detailed Hunting Workflow - T1003 Credential Dumping
    • low Risky intent intent-offensive-security references/workflows.md:48
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      ## Phase 3: Post-Dump Lateral Movement
    • low Risky intent intent-offensive-security SKILL.md:3
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
      description: Detect OS credential dumping (MITRE T1003) targeting LSASS memory, the SAM
      detector
    • low Risky intent intent-offensive-security SKILL.md:7
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      credential dumping.
    • low Risky intent intent-offensive-security SKILL.md:67
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
      # Detecting T1003 Credential Dumping with EDR
      detector
    • low Risky intent intent-offensive-security SKILL.md:88
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
      2. **Detect Credential Dumping Tools**: Hunt for known tool signatures -- Mimikatz (sekurlsa::logonpasswords), procdump.exe targeting LSASS, comsvcs.dll MiniDump, and Task Manager creating LSASS dumps
      detector
    • low Risky intent intent-offensive-security SKILL.md:92
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      6. **Correlate with Lateral Movement**: After credential dumping, attackers typically move laterally. Correlate credential access events with subsequent remote logon attempts.

    Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note frontmatter-key unknown frontmatter key "domain"
    • note frontmatter-key unknown frontmatter key "subdomain"
    • note frontmatter-key unknown frontmatter key "d3fend_techniques"
    • note frontmatter-key unknown frontmatter key "nist_csf"
    • note frontmatter-key unknown frontmatter key "mitre_attack"
    • note frontmatter-key unknown frontmatter key "mitre_f3"

    Process rating: all ten parameters 67/100

    • 0Failures and branches. Linear process with no failure handling
    • 0Progress reporting. Says nothing while it works
    • 20When it triggers. No condition that starts the skill
    • 30Running it twice. 2 mutating operations with no state check
    • 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. 23 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1433 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
    • +4Description does not say when NOT to use the skill (false activations)
    • -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
    • +3Description length 362: enough signal without eating the budget
    • +4Structure: 12 headings
    • +3Step-by-step instructions: 23 items
    • +3Output format is stated explicitly
    • +4Has examples (5 code blocks)
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.