security-arsenal

Security payloads, bypass tables, wordlists, gf pattern names, always-rejected bug list, and conditionally-valid-with-chain table. Use when you need specific payloads for XSS/SSRF/SQLi/XXE/NoSQLi/command injection/SSTI/IDOR/path-traversal/HTTP smuggling/WebSocket/MFA bypass, bypass techniques, or to check if a finding is submittable. Also use when asked about what NOT to submit.

Quality

71%

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/security-arsenal/SKILL.md

Quality

Content

42%Weight 40%Scale 1-3

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

An extremely actionable reference catalogue with concrete payloads, decision trees, and submission rules, but it violates progressive disclosure by cramming everything into one giant file and referencing scripts/sections that do not exist as bundle files. Conciseness is also weak given the volume of widely-known material restated inline.

Suggestions

Split the body into one-level-deep bundle files (e.g. references/payloads.md, references/waf-bypass.md, references/submission-rules.md) and have SKILL.md act as a concise overview that links to them, fixing the dangling tools/*.sh, tools/*.py, and 'web2-vuln-classes' references.

Trim widely-known boilerplate (basic SQLi/XSS probe syntax, full 30+ row tamper-script table) to one representative example plus a pointer, keeping only the novel, high-signal material inline.

Add a short top-of-file workflow that sequences the catalogue use (recon fingerprint -> quick-routing table -> class-specific payload -> validation verdict -> submittable/N/A check) so the existing checkpoints form one coherent process rather than scattered local ones.

Dimension	Reasoning	Score
Conciseness	At ~1600 lines the body is a monolithic reference dump with heavy repetition across payload tables and tamper-script lists; much of it restates knowledge Claude already has (common injection syntax, well-known CVE PoCs) where a pointer plus one example would suffice.	1 / 3
Actionability	Copy-paste-ready curl/sqlmap/ffuf commands, full payloads by engine, vendor-specific tamper combinations, and a 403-bypass decision tree give directly executable guidance with concrete examples throughout.	3 / 3
Workflow Clarity	The WAF bypass decision tree, verdict system (bypassed/needs_review/blocked), submittable/N/A callouts, and '5-minute rule' supply sequencing and validation checkpoints, but the document is a parallel catalogue of techniques rather than one clearly sequenced multi-step workflow, so checkpoints are local rather than global.	2 / 3
Progressive Disclosure	Everything is inline in a single ~1600-line SKILL.md with no references/ or scripts/ bundle files, yet the body repeatedly cites non-existent paths (tools/bypass_403.sh, tools/waf_response_analyzer.py, tools/waf_encoder.py, tools/multipart_mutator.py, 'web2-vuln-classes'); this is a monolithic wall with broken/un-signaled references rather than a one-level-deep overview.	1 / 3
	Total	7 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 strong, third-person description that names concrete artifact types and supplies explicit 'Use when' triggers covering both positive and negative (what NOT to submit) cases. It is comprehensive without being padded and unlikely to mis-fire for adjacent skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete deliverables — 'Security payloads, bypass tables, wordlists, gf pattern names, always-rejected bug list, and conditionally-valid-with-chain table' — naming exact artifact types rather than vague actions.	3 / 3
Completeness	Explicitly answers both what (the payload/reference tables it holds) and when via two 'Use when'/'Also use when' clauses, including the negative-trigger case ('asked about what NOT to submit').	3 / 3
Trigger Term Quality	Covers natural terms a hunter would say ('XSS/SSRF/SQLi/...SSTI/IDOR/path-traversal', 'bypass techniques', 'check if a finding is submittable', 'what NOT to submit') with broad coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	The vulnerability-specific payload catalogue and submission-validity niche is distinct and unlikely to conflict with generic security skills; triggers are tightly scoped to payload/bypass/submission decisions.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (1652 lines); consider splitting into references/ and linking	Warning
relative_links	Relative link issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: shuvonsec/claude-bug-bounty
Path: skills/security-arsenal/SKILL.md
Commit: 2009594

Reviewed: 9 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.