CtrlK
BlogDocsLog inGet started
Tessl Logo

unlimited-attack-scope

不设限原则:搜索/验证/串联/记录一切,全领域适用,被拦换路,不达不休。Use when reminding scope is unlimited across Web/APK/cloud/AI/wireless/social eng.

50

Quality

55%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/unlimited-attack-scope/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

42%

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

The body is a brief, well-organized manifesto but functions as motivational philosophy rather than actionable guidance, with no concrete tools, methods, or validation checkpoints. Its conciseness is decent though padded by rhetorical closing prose.

Suggestions

Add concrete actionable guidance: name specific search channels/tools, define what '验证' (verify) means operationally (e.g. confirm a finding reproduces before recording it as a Fact), and give decision criteria for '被拦换路' (when to abandon one path for another).

Turn search→verify→chain→record into an explicit sequenced workflow with validation checkpoints (e.g. 'verify before chaining; record negative results as Facts') to lift workflow clarity.

Remove the closing motivational blockquote (解谜 / 跳出固有框架的真正含义) — it is rhetorical padding that does not advance the skill.

DimensionReasoningScore

Conciseness

The core principle (搜索/验证/串联/记录, 被拦换路, 不达不休) is compact, but the closing blockquote about deriving a 'unique attack chain like solving a puzzle' and 'the true meaning of breaking out of inherent frameworks' is motivational prose that does not earn its tokens.

2 / 3

Actionability

It offers only abstract directives (搜索一切, 验证一切, 被拦换路) with no concrete tools, methods, examples, or decision criteria, describing a mindset rather than instructing — matching 'vague or abstract; describes rather than instructs'.

1 / 3

Workflow Clarity

An implied sequence (search → verify → chain → record) and a loose feedback notion (被拦换路) exist, but there are no explicit validation checkpoints for the destructive/batch security operations it implies, fitting 'steps listed but validation gaps'.

2 / 3

Progressive Disclosure

The skill is under 50 lines, needs no external references, and is organized into a single clear section, so per the simple-skills guideline it meets the well-organized-sections bar for a 3.

3 / 3

Total

8

/

12

Passed

Description

67%

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 answers both what and when with an explicit Use-when trigger and lists several domain keywords, but its actions are abstract and the trigger phrasing is unnatural. It carves a red-team niche yet remains broad enough to risk overlap.

Suggestions

Rewrite the trigger as natural user language a red-team operator would say (e.g. 'Use when planning or executing a penetration test / red-team engagement where scope is unconstrained across web, mobile, cloud, AI, wireless, or social engineering').

Replace abstract verbs with concrete capability statements (e.g. 'enumerate assets across web/APK/cloud, verify findings, chain low-severity issues into a full kill chain, and log negative results') to raise specificity.

Tighten distinctiveness by naming the specific deliverable (a target-specific attack chain) so it does not read as a generic 'investigate everything' security skill.

DimensionReasoningScore

Specificity

Names actions (搜索/验证/串联/记录) and domains (Web/APK/cloud/AI/wireless) but they are abstract verbs rather than concrete operations, matching the 'names domain and some actions but not comprehensive' anchor rather than the specific multi-action level 3.

2 / 3

Completeness

It states what (search/verify/chain/record everything across all domains) and has an explicit 'Use when…' trigger, so it is not capped at 2 per the guidelines and clearly answers both what and when.

3 / 3

Trigger Term Quality

Relevant domain keywords (Web, APK, cloud, AI, wireless, social eng) are present, but the 'Use when reminding scope is unlimited' framing is unusual user phrasing and misses natural trigger variations, fitting the 'some relevant keywords but missing common variations' anchor.

2 / 3

Distinctiveness Conflict Risk

The red-team/penetration-testing framing and tags carve a niche, but the '搜索一切/不设上限' (search everything / no upper limit) breadth is generic enough to overlap with other security-investigation skills, fitting 'somewhat specific but could still overlap'.

2 / 3

Total

9

/

12

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
Ed1s0nZ/CyberStrikeAI
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.