CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

web-waf-detection

Web Application Firewall fingerprinting — Cloudflare, AWS WAF, Akamai, Imperva, etc.

Quality

81%

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

SKILL.md
Quality
Evals
Security

Quality

Content

93%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 an exemplary lean, single-purpose skill: executable commands, a concrete signal lookup table, and a clear handoff note with zero wasted tokens. The only weakness is the absence of guidance for interpreting negative or ambiguous detection results.

DimensionReasoningScore

Conciseness

The body is lean and efficient: a two-sentence purpose statement, an executable command block, a compact indicator table, and a handoff note — no padding and no explanation of concepts Claude already knows.

5 / 5

Actionability

"wafw00f https://<target>" and the curl probe piping headers through grep are copy-paste ready, and the indicator table maps each WAF to concrete header/cookie signals, fully covering the common detection cases.

5 / 5

Workflow Clarity

The detection flow is clear (tool scan, manual header probe, indicator lookup, handoff note), but there is no checkpoint for ambiguous outcomes — e.g., what to conclude when no listed signal matches — leaving a minor validation gap.

4 / 5

Progressive Disclosure

At under 50 lines with no external references needed, the well-organized sections (Tooling, Known WAF Indicators, Multi-Proxy / Smuggling Signal) fully satisfy progressive disclosure for a simple single-purpose skill.

5 / 5

Total

19

/

20

Passed

Description

61%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 names a clear, distinctive niche with concrete vendor triggers, but it omits any "Use when..." trigger guidance and lists only one action, leaving completeness and specificity at mid-level. The trigger keywords that would fix this already exist in the metadata's when_to_use field and could be folded into the description itself.

Suggestions

Add a 'Use when...' clause to the description (e.g., 'Use when detecting a WAF, running wafw00f, or when Cloudflare, AWS WAF, Akamai, Imperva, or a web shield blocks requests') — this would lift both completeness and trigger-term quality.

Include natural trigger variations users actually say — the bare 'WAF' abbreviation, 'wafw00f', and 'web shield' — which currently live only in metadata.when_to_use, not the description.

Name one or two more concrete actions beyond 'fingerprinting' (e.g., 'identify WAF vendors via response headers and cookies, and flag multi-proxy stacks for request-smuggling handoff') to raise specificity.

DimensionReasoningScore

Specificity

"Web Application Firewall fingerprinting" names the domain plus one concrete action (fingerprinting), and the vendor list names targets rather than additional actions — matching the anchor for 1-2 concrete actions without comprehensive coverage.

3 / 5

Completeness

The "what" is clear (WAF fingerprinting across named vendors) but there is no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

"Cloudflare, AWS WAF, Akamai, Imperva" are natural terms users would say, giving good keyword coverage, but common variations like the bare "WAF" abbreviation, "wafw00f", and "web shield" are missing from the description field.

4 / 5

Distinctiveness Conflict Risk

WAF fingerprinting with named vendors is a clear niche with distinct triggers, but "fingerprinting" carries minor overlap risk with adjacent recon skills (tech-stack fingerprinting, general web reconnaissance), and the lack of a when-clause leaves boundaries slightly soft.

4 / 5

Total

14

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

PurpleAILAB/Decepticon

Path

packages/decepticon/decepticon/skills/standard/recon/web-recon/waf-detection/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.