SKILLEMALL.ai
GitHub ↗ RU Sign in

CD firmware-pentest

固件 / IoT 渗透链。从拿到一坨 .bin / .img 开始，闭环走完逆向 → 提取 → 模拟 → 利用。 方法论遵循 OWASP FSTM 九阶段；工具链以 binwalk v3、unblob、EMBA、Firmadyne、AFL++ 为主。 适用场景：路由器/摄像头/智能家居固件审计、固件升级包逆向、IoT CVE 复现、嵌入式 0day 挖掘。 触发关键词：固件、firmware、IoT、binwalk、unblob、UART、JTAG、squashfs、UBI、JFFS2、Firmadyne、QEMU 全系统仿真、EMBA、固件渗透、路由器固件、嵌入式漏洞利用、bootloader、NVRAM、FAT、firmware analysis toolkit。

zhaoxuya520/reverse-skill Agent Skills author: zhaoxuya520 MIT 4 files body ≈ 2 134 tokens Open the sourcegithub.com↗ analyzed 6 d ago

固件 / IoT 渗透链。从拿到一坨 .bin / .img 开始，闭环走完逆向 → 提取 → 模拟 → 利用。 方法论遵循 OWASP FSTM 九阶段；工具链以 binwalk v3、unblob、EMBA、Firmadyne、AFL++ 为主。…

As a process D 46/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

AnalyzerGitHubSecuritytype 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%
92
Quality 40%
76
Run on models
none yet
Process rating
D
46/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
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 · 8

✓ No critical or high findings

Medium and low: 8
  • low Dangerous commands cmd-privilege references/emulation-and-fuzz.md:259
    Privilege escalation / world-writable permissions (documentation of a security skill)
    sudo python3 fuzz_httpd.py
    security skill
  • low Risky intent intent-offensive-security references/emulation-and-fuzz.md:266
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    # pwntools 生成 reverse shell
  • low Dangerous commands cmd-privilege references/extraction-methodology.md:115
    Privilege escalation / world-writable permissions (documentation of a security skill)
    sudo dd if=root…fs2 of=/dev/mtdblock0
    security skill
  • low Risky intent intent-offensive-security SKILL.md:2
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    name: firmware-pentest
  • low Risky intent intent-offensive-security SKILL.md:10
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    # 固件 / IoT 渗透链 (Firmware Pentest)
  • low Risky intent intent-offensive-security SKILL.md:14
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)
    1. `NOW`: 读取 `../field-journal/precedent-pentest.md` — 确认本 skill 的操作是已授权的常规操作
    quoted
  • low Risky intent intent-offensive-security SKILL.md:37
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (documentation table row)
    | 仿真起来后做 Web/RCE 利用 | `pentest-tools/`、`attack-chain/` |
    table
  • low Risky intent intent-offensive-security SKILL.md:177
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    # pwntools 生成 MIPS reverse shell

Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")

Process rating: all ten parameters 46/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 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
  • 60Tools and files. Uses tools (bash) that frontmatter does not declare
  • 100Steps. 37 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 2134 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
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +3Description length 338: enough signal without eating the budget
  • +4Structure: 25 headings
  • +3Step-by-step instructions: 37 items
  • +4Has examples (14 code blocks)
  • +4Reference files are cited in the instructions (3 of 3)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.