wpa3-sae

WPA3-SAE transition-mode downgrade (DragonShift), SSID Confusion CVE-2023-52424, Dragonblood side-channels, and SAE captive-portal credential recovery against WPA3-Personal networks.

Quality

78%

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 ./packages/decepticon/decepticon/skills/standard/wireless/wpa3-sae/SKILL.md

Quality

Content

83%Weight 40%Scale 1-5

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

The content is a well-structured, highly actionable set of attack paths with concrete commands and evidence-capture guidance. Its weaknesses are a missing re-validation feedback loop around cracking and a referenced notes file that is not present in the bundle.

Suggestions

Add an explicit feedback loop after the hashcat step (e.g. 'If hashcat --show is empty, re-capture and retry' or a verify-then-report checkpoint) to lift workflow_clarity.

Provide the missing references/wpa3-transition-mode-notes.md file or remove the dangling reference so progressive_disclosure is fully grounded.

Trim the multi-line opening blockquote and inline expected-output comments slightly to improve token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is largely efficient with command-level detail and minimal preamble, though the opening blockquote and several inline expected-output comments add some length that could be trimmed; it largely assumes Claude's competence without explaining basics.	4 / 5
Actionability	Each path provides concrete, copy-pasteable airodump/tshark/hcxpcapngtool/hashcat/dragonslayer commands with expected output and field flags, plus ready-to-use kg_add_node evidence snippets covering the common cases.	5 / 5
Workflow Clarity	Paths A-D are clearly sequenced with numbered steps and validation cues (MFPC/MFPR decode, expected patched-target output, ZFP deliverables), and OPSEC gates on permitted_actions/posture act as checkpoints; minor gaps include no explicit re-validate feedback loop after a failed crack and the destructive deauth lacks a verification step beyond capture.	4 / 5
Progressive Disclosure	The body is well-organized into Prerequisites, four labeled Paths, Evidence, ZFP, OPSEC, and a References section with one-level-deep pointers (wpa2-psk, evil-twin-karma, deauth-pmf skills) and one named references file; however the referenced references/wpa3-transition-mode-notes.md does not exist in the bundle, slightly weakening the structure.	4 / 5
	Total	17 / 20 Passed

Description

73%Weight 40%Scale 1-5

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 highly specific and distinctive, naming four concrete attack techniques with CVE labels against a clearly scoped WPA3-Personal niche. Its main gap is the absence of an explicit 'Use when...' trigger clause in the description field itself, which caps completeness at 3.

Suggestions

Add an explicit 'Use when...' clause to the description, e.g. 'Use when assessing WPA3-Personal networks for downgrade, SSID confusion, Dragonblood, or credential recovery.'

Include a few more natural user-facing synonyms in the description (e.g. 'WiFi authentication', 'wireless password') alongside the technical SAE terms.

Dimension	Reasoning	Score
Specificity	Names multiple concrete attack actions (transition-mode downgrade, SSID Confusion, Dragonblood side-channels, SAE captive-portal credential recovery) with specific CVE/technique labels, giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	The 'what' is clearly and concretely stated (the four attack paths), but there is no 'Use when...' clause in the description itself; the when guidance lives only in the metadata.when_to_use field, so completeness is capped at 3 per the missing-trigger-clause guideline.	3 / 5
Trigger Term Quality	Strong natural terms (WPA3, SAE, Dragonblood, transition mode downgrade, WPA3-Personal, SAE handshake) but lacks common synonyms a user might say like 'WiFi authentication' or 'wireless password' and omits a parallel trigger list beyond the metadata when_to_use.	4 / 5
Distinctiveness Conflict Risk	The description carves a clear niche (WPA3-SAE downgrade/confusion/side-channel attacks against WPA3-Personal) with distinct triggers that would not fire for unrelated wireless or general-purpose skills; minimal conflict risk.	5 / 5
	Total	17 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	13 / 16 Passed

Repository: PurpleAILAB/Decepticon
Path: packages/decepticon/decepticon/skills/standard/wireless/wpa3-sae/SKILL.md
Commit: 0cf691e

Reviewed: 2 days 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.