CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

vuln-research

Research a specific CVE or vulnerability disclosure end-to-end — what version is affected, is your code reachable, is there a public PoC, is there a patch, what's the exposure window, what's the mitigation if you can't patch immediately. Use when the user mentions 'CVE,' 'vulnerability research,' 'is this CVE relevant,' 'zero-day,' 'CISA KEV,' 'GitHub Security Advisory,' 'reachability analysis,' 'patch analysis,' 'exploit availability,' 'EPSS,' 'CVSS,' or 'should we drop everything and patch this.'

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

88%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 strong, highly actionable workflow: concrete commands, explicit checkpoints, and a complete output template with a traps section for error recovery. The only deductions are minor — a slightly redundant trailing references section and small tightening/splitting opportunities.

Suggestions

Trim the trailing References section or fold it into Step 1's source list — most URLs (NVD, CISA KEV, EPSS, Exploit-DB, GreyNoise) already appear inline where they are used.

Inline the three required accept-risk fields (why / compensating controls / re-evaluation trigger) in the Output Format section itself, so the skill doesn't depend on the user having owasp-audit loaded to produce a complete disposition.

DimensionReasoningScore

Conciseness

The body is dense and assumes competence (no explaining what a CVE or npm is; 'everything downstream is summarized or sometimes wrong' earns its tokens), but the trailing References section repeats URLs already given inline in Step 1 and a few lines ('Patch Tuesday / vendor-specific cadences for context') could be trimmed — minor over-explanation, not the lean every-token-earns-its-place level.

4 / 5

Actionability

Copy-paste-ready commands throughout: 'npm ls <package>', 'git tag --contains <commit>', the grep recipes in Steps 3-4, exact source URLs, a concrete EPSS interpretation table, and a complete fill-in output template — specific executable guidance covers the common cases.

5 / 5

Workflow Clarity

Seven clearly sequenced steps with explicit validation checkpoints ('Don't write "not reachable" without showing the work'; 'confirm via npm ls / lockfile that the patched version is actually deployed'), a four-way outcome classification in Step 4, and a 'Common research traps' section serving as error-recovery guidance — feedback loops and checklist (checkbox decision items) are present.

5 / 5

Progressive Disclosure

A single-file skill with no bundle files; sections are well-organized and nothing is buried, so navigation is easy. Not 5 because minor organization gaps remain: the trailing References list duplicates inline URLs, and the accept-risk disposition leans on owasp-audit's output format (though it does restate the three required fields), leaving slight structural dependence on sibling skills.

4 / 5

Total

18

/

20

Passed

Description

100%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.

Excellent description: third-person, concrete, and comprehensive on both capability coverage and trigger phrases. It clearly delimits the niche of applicability research and includes natural colloquial trigger utterances alongside the technical acronyms.

DimensionReasoningScore

Specificity

The description enumerates six concrete capabilities — 'what version is affected, is your code reachable, is there a public PoC, is there a patch, what's the exposure window, what's the mitigation' — comprehensively covering the research arc with no gaps; it is not score 4 because coverage is complete rather than having minor gaps.

5 / 5

Completeness

It explicitly answers 'what' ('Research a specific CVE or vulnerability disclosure end-to-end') with concrete sub-questions and 'when' via a literal 'Use when the user mentions...' clause with concrete trigger phrases, matching the 5 anchor exactly.

5 / 5

Trigger Term Quality

Triggers include acronyms ('CVE,' 'EPSS,' 'CVSS,' 'CISA KEV,' 'zero-day'), technical phrases ('reachability analysis,' 'patch analysis,' 'exploit availability'), and natural user utterances ('is this CVE relevant,' 'should we drop everything and patch this') — comprehensive synonym and colloquial coverage.

5 / 5

Distinctiveness Conflict Risk

A clear niche — CVE applicability research (reachability, PoC, exposure window, mitigation) — with research-specific triggers like 'reachability analysis' and 'is this CVE relevant' that a generic audit or inventory skill would not claim; conflict risk is minimal.

5 / 5

Total

20

/

20

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

15

/

16

Passed

Repository

briiirussell/cybersecurity-skills

Path

skills/vuln-research/SKILL.md

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.