component-vuln-intel

联网情报收集:识别组件后必做CVE/搜索引擎/中文社区/GitHub PoC/资产引擎/即时情报/依赖扩展+受阻换路。Use when a framework/component/version is identified and must search before exploit.

Quality

76%

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/component-vuln-intel/SKILL.md

Quality

Content

85%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.

The body is an exceptionally lean, fully executable search playbook with a well-sequenced mandatory workflow and a genuine error-recovery feedback loop. Its main weakness is organization: everything sits in a single undifferentiated code block with no section structure, and a couple of commands mix shell syntax into browser navigation.

Suggestions

Break the single code block into markdown sections (e.g., '## Mandatory search sequence', '## When a search is blocked', '## Escalation') so the fallback ladder and main sequence are navigable at a glance.

Move the fofa lookup to a terminal command that computes the base64 query (e.g., a curl/terminal step instead of embedding $(...) substitution in a browser_navigate URL), and note that GitHub code-search API calls require an auth token.

Consider splitting the blocked-fallback ladder into a reference file (e.g., references/blocked-search.md) and signaling it clearly, keeping SKILL.md as a tight overview of the 7-step sequence.

Dimension	Reasoning	Score
Conciseness	Every line is a command, URL, or instruction; there is no explanation of concepts Claude already knows and no padding, with lean {C}/{V} templating throughout.	5 / 5
Actionability	Commands are concrete and mostly copy-paste ready (searchsploit, curl\|python3 one-liners, browser URLs), but minor gaps exist: the fofa URL embeds a $(echo -n ... \| base64) shell substitution inside a browser_navigate, and the GitHub code-search API call requires authentication it doesn't mention.	4 / 5
Workflow Clarity	A clear mandatory sequence (steps 1-7) with per-step tool assignments, an explicit error-recovery ladder triggered by concrete failure signals ("碰到403/验证码/空结果/超时→按序执行不放弃"), and a defined terminal handoff ("全部受阻仍无结果→...→转 zero-day-discovery") plus a results-verification discipline stated up front.	5 / 5
Progressive Disclosure	No bundle files exist, and the entire body is one monolithic code block with no markdown section headers; the blocked-fallback ladder is buried inline and cross-skill references (proxy-tool-bootstrap, zero-day-discovery) are not clearly signaled, though the internal numbering keeps it coherent.	3 / 5
	Total	17 / 20 Passed

Description

67%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.

The description covers a distinct niche with a concrete, near-comprehensive action list and an explicit 'Use when' trigger clause, but its telegraphic mixed-language keyword style compresses the 'what' and limits natural trigger-term coverage. Restating the actions in plain third-person verb form and adding common synonyms would lift both specificity and trigger quality.

Suggestions

Rewrite the action list as plain third-person verb phrases (e.g., 'Searches CVE databases, GitHub PoCs, Chinese security communities, and asset engines for known exploits of an identified component') instead of a slash-separated keyword string.

Add natural trigger synonyms users would actually say, such as 'vulnerability', 'known exploits', '0day', or 'check for public exploits', to broaden trigger-term coverage.

Keep the explicit 'Use when...' clause but pair it with an English (or consistently single-language) statement of what the skill does so both halves read clearly.

Dimension	Reasoning	Score
Specificity	Enumerates multiple concrete action categories ("CVE/搜索引擎/中文社区/GitHub PoC/资产引擎/即时情报/依赖扩展+受阻换路"), giving near-comprehensive coverage, but they are stated as a telegraphic slash-separated keyword list rather than clear action statements.	4 / 5
Completeness	Both what (the enumerated search procedure) and when ("Use when a framework/component/version is identified and must search before exploit") are present; the 'what' is explicit but compressed into a dense keyword enumeration that could be more clearly stated.	4 / 5
Trigger Term Quality	Relevant keywords are present ("framework/component/version", "CVE", "exploit", "PoC") with an explicit trigger clause, but common natural variations users would say ("vulnerability lookup", "known exploits", "0day") are missing.	3 / 5
Distinctiveness Conflict Risk	A clear niche (post-identification exploit/vulnerability intel gathering) with specific triggers; only minor overlap risk with generic recon or search-oriented skills.	4 / 5
	Total	15 / 20 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
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: AIPentest/CyberStrikeAI
Path: skills/component-vuln-intel/SKILL.md
Commit: 470eb5e

Reviewed: 2 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.