CtrlK
BlogDocsLog inGet started
Tessl Logo

shiro-attack-cli

当用户要求利用、检测或测试 Apache Shiro rememberMe 反序列化漏洞 (Shiro-550, CVE-2016-4437) 时使用。触发词包括 "Shiro"、"rememberMe"、"shiro attack"、"CVE-2016-4437"、"Shiro-550"、"爆破 Shiro key"、"利用 Shiro"、"Shiro 漏洞"。覆盖单目标探测、密钥爆破、Gadget 链自动检测、命令执行、内存马注入和 Key 修改。

76

Quality

93%

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

87%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 efficient, fully actionable CLI reference with a clear end-to-end flow example. The only gap is the absence of explicit validation/verification checkpoints between destructive steps (exec, memshell, changekey), which caps workflow clarity.

Suggestions

Add validation checkpoints in the full-flow example, e.g. 'verify detect outputs [++] 存在shiro框架! before running crack' and 'confirm crack finds a key before exec/memshell/changekey'.

Add a brief feedback loop after exec and memshell (check shell/memshell connection succeeds; if '响应含 rememberMe=deleteMe', switch gadget/echo/AES mode and retry).

Make the AES-mode decision an explicit precondition before crack/exec rather than only a passive table (e.g. note that --cbc is default for ≤1.2.4 and try --gcm on failure).

DimensionReasoningScore

Conciseness

Lean CLI reference with no padding about what Shiro deserialization is; every section (commands, options, AES-mode table, errors, full example) earns its place and assumes Claude's competence; not score 2 because there is no unnecessary explanation to tighten.

3 / 3

Actionability

Fully executable commands with concrete options, stated defaults, and a copy-paste-ready "完整流程示例"; not score 2 because guidance is complete and runnable rather than pseudocode or missing key details.

3 / 3

Workflow Clarity

The full-flow example gives a clear 5-step sequence (detect → crack → exec → memshell → changekey) but lacks explicit validation checkpoints for destructive steps (no 'verify detect/crack succeeded before proceeding'); per the feedback-loops note this caps at 2 rather than 3.

2 / 3

Progressive Disclosure

No bundle files exist; the single SKILL.md is well-organized into clear sections (启动方式, 准备工作, 命令, AES 模式, JSON 输出, 常见错误, 完整流程示例) appropriate for a single-purpose CLI reference; not score 2 because structure and navigation are clean with no nested references.

3 / 3

Total

11

/

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, well-scoped description: explicit trigger guidance, a concrete capability list, and a distinctive Apache Shiro-550 niche. Voice and trigger terms follow best practice.

DimensionReasoningScore

Specificity

Lists multiple concrete capabilities — "单目标探测、密钥爆破、Gadget 链自动检测、命令执行、内存马注入和 Key 修改" — matching the score-3 anchor; not score 2 because actions are specific and comprehensive rather than partial. Uses third-person trigger voice ("当用户要求...时使用").

3 / 3

Completeness

Answers both what (the 覆盖... capability list) and when with an explicit 'Use when...' clause ("当用户要求利用、检测或测试...时使用"); not score 2 because the when is explicit, not merely implied.

3 / 3

Trigger Term Quality

Explicit trigger list ("触发词包括" Shiro, rememberMe, shiro attack, CVE-2016-4437, Shiro-550, 爆破 Shiro key, 利用 Shiro, Shiro 漏洞) gives good natural-term coverage users would actually say; not score 2 because both common names and the CVE ID are present.

3 / 3

Distinctiveness Conflict Risk

Niche is clearly scoped to Apache Shiro rememberMe deserialization (Shiro-550 / CVE-2016-4437) with distinct triggers unlikely to collide with other skills; not score 2 because the domain is narrow and unambiguous.

3 / 3

Total

12

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
SummerSec/ShiroAttack2
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.