SKILLEMALL.ai
GitHub ↗ RU Sign in

CC fleet-hunting-with-velociraptor

Deploy a Velociraptor server and agents, then author VQL (Velociraptor Query Language) artifacts and run them as fleet-wide hunts, on-demand forensic collections, or standalone offline collectors. Use when hunting a TTP across hundreds or thousands of endpoints, collecting forensic artifacts during incident response without re-imaging, or generating collectors for unmanaged/air-gapped hosts.

mukul975/Anthropic-Cybersecurity-Skills Agent Skills author: mukul975 Apache-2.0 5 files · 1 script body ≈ 2 044 tokens Open the sourcegithub.com↗ analyzed 5 d ago

Deploy a Velociraptor server and agents, then author VQL (Velociraptor Query Language) artifacts and run them as fleet-wide hunts, on-demand forensic…

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

ProcedureGitHubPeople and hiringtype 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
79/100
safety, quality, tests
Safety 60%
83
Quality 40%
73
Run on models
none yet
Process rating
C
51/100
Has gaps
Result and completion w 14
0
Failures and branches w 10
0
When it triggers w 12
20
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.

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 · 5

    ✓ No critical or high findings

    Medium and low: 5
    • medium Dangerous commands cmd-encoded-exec scripts/agent.py:147
      Executes a base64/encoded payload (detector / deny-list definition; string literal in code, not executed)
      default="(?i)(-enc|from…ing|downloadstring|-w hidden|iex)")
      detectorcode literal
    • low Risky intent intent-offensive-security references/standards.md:7
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      | DE.CM-01 | Networks and network services are monitored to find potentially adverse events | Velociraptor provides continuous endpoint visibility and on-demand fleet hunts that surface adverse events
    • low Dangerous commands cmd-privilege SKILL.md:48
      Privilege escalation / world-writable permissions (documentation of a security skill)
      sudo mv velo…v0.*-lin…d64 /usr/local/bin/velociraptor
      security skill

    A further 2 matches are quotations in this security skill's documentation and are not counted as findings.

    Files scanned: 5. 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 "nist_csf"
    • note frontmatter-key unknown frontmatter key "mitre_attack"

    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
    • 20When it triggers. No condition that starts the skill
    • 30Running it twice. 10 mutating operations with no state check
    • 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 85Steps. 22 steps, 1 vague phrases
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 2044 tokens
    • 100Progress reporting. Reports progress
    • low The response is described with custom markup (4 tags): a typed call is more reliable

    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
    • -2localhost URLs: will not work for another user
    • -42 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 394: enough signal without eating the budget
    • +4Structure: 19 headings
    • +3Step-by-step instructions: 22 items
    • +4Has examples (11 code blocks)
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 73.