wireless-hardware-attack

无线/硬件:WiFi PMKID/WPS/Evil Twin,BLE,Zigbee,NFC,SDR,UART/JTAG/SPI,侧信道,故障注入。Use when attacking WiFi, BLE, RFID, SDR, or hardware interfaces.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/wireless-hardware-attack/SKILL.md

Quality

Content

60%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is an extremely token-efficient, well-organized cheat sheet of concrete attack tools, but it is a flat reference list: it lacks executable command syntax for most techniques and provides no sequenced workflow or validation checkpoints for the risky multi-step operations it covers.

Suggestions

Add minimal runnable command syntax for the key flows (e.g. hcxdumptool + hashcat PMKID, gatttool read, binwalk -Me) so guidance is copy-paste-ready rather than just tool names.

Provide a short sequenced workflow with validation checkpoints for the riskiest operations (firmware dump/JTAG, fault injection), e.g. dump → verify image with binwalk → confirm before injecting, so failures are caught early.

Move per-protocol detail into reference files (references/wifi.md, references/hardware.md) and keep SKILL.md as a one-level-deep overview with clearly signaled links, to scale the dense inline list into proper progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is a lean, dense cheat sheet of named tools and techniques (aircrack-ng, hcxdumptool, hashcat, proxmark3, rtl-sdr, binwalk -Me) with no concept explanations Claude already knows, matching the 'every token earns its place' anchor.	3 / 3
Actionability	It names specific tools and one runnable command ("binwalk -Me"), but most entries are tool/approach lists (e.g. "aircrack-ng/PMKID(hcxdumptool+hashcat)/WPS reaver") rather than copy-paste-ready command syntax, so it is concrete but incomplete — not the level-3 'fully executable' anchor.	2 / 3
Workflow Clarity	The body is a flat categorized reference list with no sequenced multi-step process and no validation/verification checkpoints for risky operations like fault injection or firmware dump, matching the 'steps unclear or missing' anchor rather than the level-2 'steps listed' anchor.	1 / 3
Progressive Disclosure	The skill is under 50 lines with no external references and a single well-organized section grouping attacks by category (WiFi / BLE / Zigbee / NFC / SDR / 硬件), qualifying for the simple-skill exception that allows a 3 with just well-organized sections.	3 / 3
	Total	9 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is concise yet specific: it enumerates concrete wireless/hardware attack techniques and pairs them with an explicit, natural-language 'Use when...' trigger in third-person voice. It cleanly answers both what the skill does and when to invoke it.

Dimension	Reasoning	Score
Specificity	Lists many concrete capabilities and techniques — "WiFi PMKID/WPS/Evil Twin", "BLE", "Zigbee", "NFC", "SDR", "UART/JTAG/SPI", "侧信道", "故障注入" — matching the anchor for multiple specific concrete actions rather than vague language.	3 / 3
Completeness	It states what (the enumerated wireless/hardware attack techniques) and when ("Use when attacking WiFi, BLE, RFID, SDR, or hardware interfaces."), with an explicit trigger clause, so it is not capped at 2.	3 / 3
Trigger Term Quality	The clause "Use when attacking WiFi, BLE, RFID, SDR, or hardware interfaces" provides good coverage of natural terms a user would say, matching the score-3 anchor; it is not generic jargon and not merely 'Works with X'.	3 / 3
Distinctiveness Conflict Risk	The wireless/hardware attack niche with distinct trigger terms (WiFi, BLE, RFID, SDR, hardware interfaces) is unlikely to overlap with unrelated skills, matching the clear-niche score-3 anchor.	3 / 3
	Total	12 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: Ed1s0nZ/CyberStrikeAI
Path: skills/wireless-hardware-attack/SKILL.md
Commit: dad14c5

Reviewed: about 15 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.