SKILLEMALL.ai
GitHub ↗ RU Sign in

BC detecting-living-off-the-land-attacks

Detect abuse of legitimate Windows binaries (LOLBins) used for living off the land attacks. Monitors process creation, command-line arguments, and parent-child relationships to identify suspicious LOLBin execution patterns.

mukul975/Anthropic-Cybersecurity-Skills Agent Skills author: mukul975 Apache-2.0 4 files · 1 script body ≈ 4 529 tokens Open the sourcegithub.com↗ analyzed 5 d ago

Detect abuse of legitimate Windows binaries (LOLBins) used for living off the land attacks.

As a process C 55/100 · Has gaps — weak spots: result and completion, failures and branches, running it twice

AnalyzerGitHubInfrastructuretype 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
B
90/100
safety, quality, tests
Safety 60%
98
Quality 40%
79
Run on models
none yet
Process rating
C
55/100
Has gaps
Result and completion w 14
0
Failures and branches w 10
0
Running it twice w 4
30
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 · 2

    ✓ No critical or high findings

    Medium and low: 2
    • low Risky intent intent-offensive-security SKILL.md:143
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      a common LOLBin technique for payload delivery (LOLBAS T1105).
    • low Risky intent intent-offensive-security SKILL.md:450
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      # WMI provider spawning processes (lateral movement)

    Files scanned: 4. 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 edit-residue the text marks something as outdated (lines 169): check that old rules are not kept next to new ones — the full check reads the text for contradictions

    Process rating: all ten parameters 55/100

    • 0Result and completion. Does not say what the result is
    • 0Failures and branches. Linear process with no failure handling
    • 30Running it twice. 5 mutating operations with no state check
    • 50When it triggers. No condition that starts the skill
    • 60Tools and files. Uses tools (python) that frontmatter does not declare
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 70Execution cost. Instruction body is 4529 tokens
    • 100Steps. 20 steps
    • 100Consistency. Name and required fields are in place
    • 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
    • +3Output format is not stated: the model decides each time
    • -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 223: enough signal without eating the budget
    • +4Structure: 11 headings
    • +3Step-by-step instructions: 20 items
    • +4Has examples (9 code blocks)
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.