SKILLEMALL.ai
GitHub ↗ RU Sign in

CC hunting-bootkits-in-efi-system-partition

Baseline the EFI System Partition and hunt malicious EFI binaries such as ESPecter, BlackLotus, Bootkitty, and Glupteba by mounting the ESP, hashing and verifying boot loaders, scanning with YARA, and flagging anomalous non-EFI files or out-of-band bootloader changes. Use during proactive threat hunts for firmware/bootkit persistence (MITRE ATT&CK T1542.003) or when investigating suspected UEFI-level compromise that survives OS reinstall.

mukul975/Anthropic-Cybersecurity-Skills Agent Skills author: mukul975 Apache-2.0 5 files · 1 script body ≈ 2 990 tokens Open the sourcegithub.com↗ analyzed 5 d ago

Baseline the EFI System Partition and hunt malicious EFI binaries such as ESPecter, BlackLotus, Bootkitty, and Glupteba by mounting the ESP, hashing and…

As a process C 60/100 · 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
88/100
safety, quality, tests
Safety 60%
97
Quality 40%
75
Run on models
none yet
Process rating
C
60/100
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

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 · 3

    ✓ No critical or high findings

    Medium and low: 3
    • low Dangerous commands cmd-privilege scripts/agent.py:12
      Privilege escalation / world-writable permissions (string literal in code, not executed)
      sudo python3 esp_bootkit_hunter.py --esp /mnt/esp --baseline base…256
      code literal
    • low Dangerous commands cmd-privilege scripts/agent.py:13
      Privilege escalation / world-writable permissions (string literal in code, not executed)
      sudo python3 esp_bootkit_hunter.py --device /dev/sda1 --mount --yara bootkit.yar
      code literal
    • low Dangerous commands cmd-privilege SKILL.md:180
      Privilege escalation / world-writable permissions (documentation of a security skill)
      sudo dd if=/dev/sda1 of=/evidence/esp_$(hostname)_$(date +%F).img bs=4M conv=noerror,sync
      security skill

    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 60/100

    • 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. 4 mutating operations with no state check
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 100Tools and files. No external tools needed
    • 100Steps. 31 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 2990 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
    • -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 442: enough signal without eating the budget
    • +4Structure: 19 headings
    • +3Step-by-step instructions: 31 items
    • +4Has examples (10 code blocks)
    • +1License stated

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