Content
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A lean, code-dense attack reference that is highly actionable and well-organized, with strong conciseness and clean progressive disclosure. Its main gaps are a couple of non-executable/placeholder examples and the absence of validation checkpoints around the destructive and batch operations.
Suggestions
Replace the described WS-Security brute ('cycle a username dict, observe response time/error class') and the '<soap:Envelope>...PublicMethod body...</soap:Envelope>' placeholder with concrete, runnable examples to reach full actionability.
Add explicit validation/verification checkpoints (e.g., confirm a captured SOAP fault or credential before proceeding, rate-limit the brute loop) so the destructive/batch operations meet the workflow-clarity bar of 3.
Consider extracting the longer payload templates (e.g., a full ws-attack.xml) into a references/ file referenced one level deep, which would keep the overview even tighter while preserving actionability.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is code-heavy and assumes Claude's competence — concrete curl/zeep/xmllint blocks and XML payloads with only brief, attack-relevant prose; it does not explain basic concepts Claude already knows, matching the 'lean and efficient; every token earns its place' anchor. | 3 / 3 |
Actionability | Most blocks are copy-paste ready (XXE payload, WSDL discovery, zeep one-liner, SOAPAction header), but the WS-Security brute is described rather than executed ('cycle a username dict, observe response time/error class') and the SOAPAction body is a placeholder ('<soap:Envelope>...PublicMethod body...</soap:Envelope>'), so it falls short of fully executable everywhere. | 2 / 3 |
Workflow Clarity | Sections are organized into a loose Discovery → attack catalog → Tooling → OPSEC flow, but there are no validation/verification checkpoints, and the batch brute and XML-bomb operations are destructive/batch in nature — the guideline caps workflow clarity at 2 when such feedback loops are missing. | 2 / 3 |
Progressive Disclosure | The skill is a single self-contained, well-sectioned file with no nested references; external pointers are clearly signaled in a References section and via 'see the SAML skill for full XSW patterns', giving easy navigation without monolithic walls or deep reference chains. | 3 / 3 |
Total | 10 / 12 Passed |