CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

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
SKILL.md
Quality
Evals
Security

Quality

Content

78%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.

A dense, practitioner-grade skill body: executable commands with expected outputs, explicit decision branches, OPSEC gating, and evidence schemas. The weaknesses are the dangling references/wpa3-transition-mode-notes.md file (no references/ directory exists) and Paths B/D being comment-level guidance that depends on other skills rather than self-contained steps.

Suggestions

Create references/wpa3-transition-mode-notes.md (or remove the citation) so the sole external reference is not a broken pointer.

Add an explicit validate-then-proceed step in Path A (e.g., confirm the 4-way handshake/PMKID was captured in the .hc22000 output before invoking hashcat).

For Path B, replace or supplement the comment-only rogue-AP block with a minimal concrete command sequence (hostapd config sketch or the exact evil-twin-karma invocation), even if the full setup remains in the referenced skill.

DimensionReasoningScore

Conciseness

The body is nearly all operational content — tool prerequisites, targeted commands, expected outputs, and gating conditions — with zero padding explaining what WPA3/SAE is or how the tools work. The opening blockquote and per-path viability notes are engagement-relevant judgment calls, not restated common knowledge, so every section earns its tokens.

5 / 5

Actionability

Paths A and C are copy-paste ready with real commands, specific tshark display filters, hashcat mode 22000, and expected output samples ("TargetSSID 1 0", "status 77"). Paths B and D, however, are comment-only blocks describing steps without executable commands, deferring to other skills — concrete guidance with minor gaps rather than fully executable throughout.

4 / 5

Workflow Clarity

Each path is numbered with an explicit target signature, branch conditions ("MFPC=1 MFPR=1 → PMF required → downgrade blocked; pivot to Path B/C/D"), and validation checkpoints (expected tshark output; "Expected result on patched target... Mark as not_vulnerable"; ZFP evidence checklist). It falls short of 5 because there are no explicit validate-then-retry loops (e.g., verify the handshake was captured before running hashcat, or re-check MFP state after remediation).

4 / 5

Progressive Disclosure

In-body structure is good (per-path sections, references section, one-level-deep pointers), but the bundle contains no references/ directory at all — the one cited reference, `references/wpa3-transition-mode-notes.md`, does not exist, so the single external navigation pointer is broken. References are clearly signaled but the actual bundle structure does not back them.

3 / 5

Total

16

/

20

Passed

Description

66%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.

A specific, well-scoped description that names all four attack paths with CVE identifiers and natural domain keywords, in correct third-person voice. Its main deficiency is the absence of an explicit "Use when..." trigger clause, which leaves the 'when to use' only weakly implied.

Suggestions

Append a trigger clause, e.g.: "Use when auditing WPA3-Personal/SAE networks, when transition mode or PMF downgrade is suspected, or when the user mentions Dragonblood, SSID confusion, or SAE handshake issues."

Add missing natural trigger terms such as "PMF/MFP", "dragonfly handshake", and "WPA3 downgrade" to broaden keyword coverage.

Consider leading with action verbs (e.g., "Audits and attacks WPA3-SAE networks via...") to make the capability phrasing more explicitly action-oriented.

DimensionReasoningScore

Specificity

The description enumerates four concrete, named attack capabilities — "transition-mode downgrade (DragonShift), SSID Confusion CVE-2023-52424, Dragonblood side-channels, and SAE captive-portal credential recovery" — matching the body's four paths. It falls just short of the 5 anchor because these are noun phrases naming attacks rather than explicit action verbs ("Extract...", "Fill..."), and the scope qualifier "against WPA3-Personal networks" is the only framing of what the skill does with them.

4 / 5

Completeness

The 'what' is clear and concrete (the four attack techniques), but there is no "Use when..." clause or equivalent explicit trigger guidance — usage is only weakly implied by "against WPA3-Personal networks". Per the judging guideline, a missing explicit 'when' clause caps completeness at 3.

3 / 5

Trigger Term Quality

Strong natural keywords a user with this need would say: "WPA3-SAE", "transition-mode downgrade", "SSID Confusion", "Dragonblood", "captive-portal", "WPA3-Personal", plus a CVE number. A few common variations are absent ("PMF/MFP", "dragonfly handshake", "downgrade attack"), which fits the 'good coverage, a few natural terms missing' anchor rather than the comprehensive-synonyms anchor.

4 / 5

Distinctiveness Conflict Risk

The WPA3-SAE niche is clear and the CVE/named-attack terms are highly distinctive, so it is unlikely to trigger for unrelated skills. However, it sits in a family of closely related wireless skills the body itself cross-references (wpa2-psk, evil-twin-karma, deauth-pmf), and terms like "transition-mode downgrade" and "credential recovery" have minor overlap risk with those — matching the 'mostly distinct; minor overlap risk' anchor.

4 / 5

Total

15

/

20

Passed

Validation

81%

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

CriteriaDescriptionResult

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

Reviewed

Table of Contents

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.