SKILLEMALL.ai
GitHub ↗ RU Sign in

CB performing-firmware-malware-analysis

Analyzes firmware images for embedded malware, backdoors, and unauthorized modifications in routers, IoT devices, UEFI/BIOS, and embedded systems, covering firmware extraction, filesystem analysis, binary reverse engineering, and bootkit detection. Use for firmware security analysis, IoT malware investigation, UEFI rootkit detection, or embedded device compromise assessment.

mukul975/Anthropic-Cybersecurity-Skills Agent Skills author: mukul975 Apache-2.0 4 files · 1 script body ≈ 2 780 tokens Open the sourcegithub.com↗ analyzed 5 d ago

Analyzes firmware images for embedded malware, backdoors, and unauthorized modifications in routers, IoT devices, UEFI/BIOS, and embedded systems, covering…

As a process B 66/100 · Nearly there — weak spots: failures and branches, progress reporting

AnalyzerSecuritytype 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
86/100
safety, quality, tests
Safety 60%
89
Quality 40%
82
Run on models
none yet
Process rating
B
66/100
Nearly there
Failures and branches w 10
0
Progress reporting w 2
0
When it triggers w 12
50
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 · 7

    ✓ No critical or high findings

    Medium and low: 7
    • medium Dangerous commands cmd-persistence SKILL.md:299
      Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation of a security skill)
      [!] /etc/crontab modified
      security skill
    • 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: Firmware Malware Analysis
    • low Risky intent intent-offensive-security SKILL.md:34
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      # Performing Firmware Malware Analysis
    • low Dangerous commands cmd-privilege SKILL.md:200
      Privilege escalation / world-writable permissions (documentation of a security skill)
      sudo cp /usr/bin/qemu-arm-static /mnt/firmware/usr/bin/
      security skill
    • low Risky intent intent-offensive-security SKILL.md:264
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      6. Check for hardcoded credentials, unauthorized SSH keys, and reverse shell scripts
    • low Risky intent intent-offensive-security SKILL.md:276
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      FIRMWARE MALWARE ANALYSIS REPORT
    • low Risky intent intent-offensive-security SKILL.md:292
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      Function: Reverse shell to 185.220.101[.]42:4444

    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 "nist_csf"
    • note frontmatter-key unknown frontmatter key "mitre_attack"
    • note edit-residue the text marks something as outdated (lines 205): check that old rules are not kept next to new ones — the full check reads the text for contradictions

    Process rating: all ten parameters 66/100

    • 0Failures and branches. Linear process with no failure handling
    • 0Progress reporting. Says nothing while it works
    • 50When it triggers. No condition that starts the skill
    • 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
    • 60Result and completion. Output format stated, no completion criterion
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 100Steps. 27 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 2780 tokens
    • 100Running it twice. No mutating operations

    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
    • -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 377: enough signal without eating the budget
    • +4Structure: 15 headings
    • +3Step-by-step instructions: 27 items
    • +3Output format is stated explicitly
    • +4Has examples (8 code blocks)
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.