competition-request-normalization-smuggling

Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for parser differentials, HTTP normalization gaps, ambiguous headers, path decoding drift, transfer-framing mismatches, and request smuggling routes. Use when the user asks to trace proxy and backend parse differences, conflicting path normalization, Host or forwarded-header ambiguity, CL/TE issues, or routing outcomes that differ across hops. Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here.

Quality

89%

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

Quality

Content

86%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 concise, well-structured instruction-only skill body that assumes Claude's competence and routes detail to one real reference file. The workflow is clearly sequenced with proof and reproduction checkpoints, though an explicit retry/feedback loop on failed reproduction would raise workflow clarity further.

Suggestions

Add an explicit feedback loop: if the minimal differential request does not reproduce a decisive effect, instruct Claude to widen or re-target the canonicalization delta and re-prove, mirroring the validate-fix-retry pattern.

Optionally include one minimal paired-request example (baseline vs. differential) inline to make the 'Capture one accepted baseline request and one minimal delta' step copy-paste concrete.

Dimension	Reasoning	Score
Conciseness	Lean and efficient — short sections and bullets assume Claude already knows CL/TE, path normalization, and transfer framing, with no padded explanations of what request smuggling is.	5 / 5
Actionability	Concrete procedural guidance ('Map every parsing hop', 'Capture one accepted baseline request and one minimal delta', 'Prove which hop interprets the request differently') is specific and actionable for an instruction-only skill, though it offers no executable code or commands.	4 / 5
Workflow Clarity	A clear 5-step Quick Start and a 3-phase Workflow with proof/reproduction checkpoints ('Prove which hop', 'Reproduce one minimal differential path') plus a handoff decision, but there is no explicit validate-fix-retry feedback loop.	4 / 5
Progressive Disclosure	Well-organized overview (Quick Start, Workflow, Read This Reference, What To Preserve) with a single one-level-deep reference that is clearly signaled and verified to exist at references/request-normalization-smuggling.md.	5 / 5
	Total	18 / 20 Passed

Description

92%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 precise, well-bounded downstream-skill description that names concrete capabilities, provides explicit trigger phrases, and includes a clear parent-skill gating condition. The only minor gap is absence of common synonyms such as 'HTTP desync'.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capability areas — 'parser differentials, HTTP normalization gaps, ambiguous headers, path decoding drift, transfer-framing mismatches, and request smuggling routes' — giving comprehensive coverage of the request-smuggling domain rather than vague abstractions.	5 / 5
Completeness	Explicitly answers both what ('CTF-sandbox workflow for parser differentials... request smuggling routes') and when ('Use when the user asks to trace... Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions').	5 / 5
Trigger Term Quality	Strong natural terms a security tester would say ('CL/TE issues', 'Host or forwarded-header ambiguity', 'request smuggling routes', 'proxy and backend parse differences'), but common synonyms like 'HTTP desync' or 'request desync' are absent.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (request smuggling / parser differentials) and adds an explicit boundary gate ('Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here'), minimizing conflict with sibling skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: zhaoxuya520/reverse-skill
Path: CTF-Sandbox-Orchestrator/competition-request-normalization-smuggling/SKILL.md
Commit: 7e2097f

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.