SKILLEMALL.ai
GitHub ↗ RU Sign in

DC performing-credential-access-with-lazagne

Extract stored credentials from compromised endpoints using the LaZagne post-exploitation tool to recover passwords from browsers, databases, system vaults, and applications during authorized red team operations.

mukul975/Anthropic-Cybersecurity-Skills Agent Skills author: mukul975 Apache-2.0 8 files · 2 scripts body ≈ 1 821 tokens Open the sourcegithub.com↗ analyzed 5 d ago

Extract stored credentials from compromised endpoints using the LaZagne post-exploitation tool to recover passwords from browsers, databases, system vaults…

As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, failures and branches

ProcedureInfrastructuretype 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
D
59/100
safety, quality, tests
Safety 60%
48
Quality 40%
75
Run on models
none yet
Process rating
C
51/100
Has gaps
Result and completion w 14
0
Failures and branches w 10
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Exfiltration medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

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.

For the author

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

    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 · 20

    ✓ No critical or high findings

    Medium and low: 20
    • medium Exfiltration intent-browser-credential-store references/standards.md:29
      Accesses a browser credential / cookie store (documentation of a security skill)
      - Chrome Login Data file access monitoring
      security skill
    • medium Dangerous commands cmd-persistence scripts/agent.py:26
      Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
      r"SOFTWARE\Microsoft\Windows\CurrentVersion\Run",
      code literal
    • medium Exfiltration intent-browser-credential-store scripts/agent.py:36
      Accesses a browser credential / cookie store (quoted — discussed, not commanded)
      r"%LOCALAPPDATA%\Google\Chrome\User Data\Default\Login Data",
      quoted
    • medium Exfiltration intent-browser-credential-store scripts/agent.py:37
      Accesses a browser credential / cookie store (detector / deny-list definition)
      r"%APPDATA%\Opera Software\Opera Stable\Login Data",
      detector
    • medium Exfiltration intent-browser-credential-store scripts/agent.py:40
      Accesses a browser credential / cookie store (quoted — discussed, not commanded)
      os.path.expanduser("~/.config/google-chrome/Default/Login Data"),
      quoted
    • medium Exfiltration intent-browser-credential-store scripts/agent.py:179
      Accesses a browser credential / cookie store (quoted — discussed, not commanded)
      (os.path.join(localappdata, "Google", "Chrome", "User Data", "Default", "Login Data"), "Chrome"),
      quoted
    • medium Exfiltration intent-browser-credential-store scripts/agent.py:184
      Accesses a browser credential / cookie store (quoted — discussed, not commanded)
      (os.path.expanduser("~/.config/google-chrome/Default/Login Data"), "Chrome"),
      quoted
    • medium Exfiltration intent-browser-credential-store SKILL.md:246
      Accesses a browser credential / cookie store (documentation of a security skill)
      | Access to Chrome Login Data SQLite DB | File access monitoring on browser credential stores |
      security skill
    • low Risky intent intent-offensive-security assets/template.md:1
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      # LaZagne Credential Harvesting Report Template
    • low Risky intent intent-offensive-security assets/template.md:25
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      ## Lateral Movement Opportunities
    • low Dangerous commands cmd-privilege references/api-reference.md:43
      Privilege escalation / world-writable permissions (documentation of a security skill)
      # Linux: sudo python laZagne.py all
      security skill
    • low Risky intent intent-offensive-security references/standards.md:22
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - Atomic Red Team T1555: https://atomicredteam.io/credential-access/T1555/
    • low Risky intent intent-offensive-security references/workflows.md:3
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      ## Credential Harvesting Workflow
    • low Risky intent intent-offensive-security references/workflows.md:30
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      5. Lateral Movement
    • low Risky intent intent-offensive-security references/workflows.md:32
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      ├── Repeat credential harvesting on new targets
    • low Risky intent intent-offensive-security SKILL.md:5
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      and applications during authorized red team operations.
    • low Risky intent intent-offensive-security SKILL.md:71
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      LaZagne is an open-source post-exploitation tool designed to retrieve credentials stored on local systems. It supports Windows, Linux, and macOS, with the most extensive module library for Windows. La
    • low Risky intent intent-offensive-security SKILL.md:83
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - Familiarity with red teaming concepts and tools
    • low Risky intent intent-offensive-security SKILL.md:92
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - Parse and prioritize recovered credentials for lateral movement
    • low Risky intent intent-offensive-security SKILL.md:94
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - Document credential harvesting results with appropriate evidence handling

    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 51/100

    • 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
    • 20When it triggers. No condition that starts the skill
    • 30Running it twice. 3 mutating operations with no state check
    • 60Tools and files. Uses tools (web, python) that frontmatter does not declare
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 100Steps. 45 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1821 tokens
    • low 10 top-level sections: this looks like several domains in one skill

    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
    • -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 212: enough signal without eating the budget
    • +4Structure: 16 headings
    • +3Step-by-step instructions: 45 items
    • +4Has examples (7 code blocks)
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.