/cve-research
Use when checking a specific dependency or package version for known CVEs and security advisories.
$ npx -y skills add fusengine/agents --skill cve-research --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/cve-research
Context preview
The summary Claude sees to decide when to auto-load this skill.
Use when checking a specific dependency or package version for known CVEs and security advisories.
SKILL.md
cve-research.SKILL.mdname: cve-research
description: "Use when checking a specific dependency or package version for known CVEs and security advisories."
argument-hint: "<package-name> [version]"
user-invocable: true
<objective> This skill researches known vulnerabilities for a specific dependency across multiple sources: OSV.dev (npm, PyPI, Go, crates, Maven), NVD (CVSS scoring), GitHub Advisory Database (maintainer responses), and Exa web search for advisories not yet indexed.
It queries OSV.dev first for speed and accuracy, cross-checks NVD for CVSS scoring, uses Exa for recent advisories, and checks GitHub Advisory for maintainer responses, then cross-references findings and prioritizes by CVSS score and exploitability — CRITICAL (9.0-10.0) fixed immediately, HIGH (7.0-8.9) before merge, MEDIUM (4.0-6.9) planned, LOW (0.1-3.9) documented — reporting fix versions and workarounds.
Out of scope: this is a single-dependency lookup, not a full project dependency sweep (use dependency-audit for that). </objective>
CVE Research Skill
Overview
Research known vulnerabilities for project dependencies using multiple sources.
Data Sources
| Source | API | Coverage | |--------|-----|----------| | NVD | nvd.nist.gov/vuln/api | All CVEs | | OSV.dev | api.osv.dev | npm, PyPI, Go, crates, Maven | | GitHub Advisory | github.com/advisories | npm, pip, composer, cargo | | Exa Search | Via MCP | Real-time web search |
Workflow
1. **Extract** dependencies from project (package.json, etc.) 2. **Query** each source for known CVEs 3. **Cross-reference** findings across sources 4. **Prioritize** by CVSS score and exploitability 5. **Report** with fix versions and workarounds
Query Strategy
For each dependency: 1. Search OSV.dev first (fastest, most accurate for packages) 2. Cross-check NVD for CVSS scoring 3. Use Exa for recent advisories not yet in databases 4. Check GitHub Advisory for maintainer responses
Severity Mapping
| CVSS Score | Severity | Action | |------------|----------|--------| | 9.0 - 10.0 | CRITICAL | Fix immediately | | 7.0 - 8.9 | HIGH | Fix before merge | | 4.0 - 6.9 | MEDIUM | Plan fix | | 0.1 - 3.9 | LOW | Document |
References
- [CVE APIs Reference](references/cve-apis.md)
- [Query Templates](references/templates/cve-query.md)
Read more
name: cve-research description: "Use when checking a specific dependency or package version for known CVEs and security advisories." argument-hint: "<package-name> [version]" user-invocable: true
<objective> This skill researches known vulnerabilities for a specific dependency across multiple sources: OSV.dev (npm, PyPI, Go, crates, Maven), NVD (CVSS scoring), GitHub Advisory Database (maintainer responses), and Exa web search for advisories not yet indexed.
It queries OSV.dev first for speed and accuracy, cross-checks NVD for CVSS scoring, uses Exa for recent advisories, and checks GitHub Advisory for maintainer responses, then cross-references findings and prioritizes by CVSS score and exploitability — CRITICAL (9.0-10.0) fixed immediately, HIGH (7.0-8.9) before merge, MEDIUM (4.0-6.9) planned, LOW (0.1-3.9) documented — reporting fix versions and workarounds.
Out of scope: this is a single-dependency lookup, not a full project dependency sweep (use dependency-audit for that). </objective>
CVE Research Skill
Overview
Research known vulnerabilities for project dependencies using multiple sources.
Data Sources
| Source | API | Coverage | |--------|-----|----------| | NVD | nvd.nist.gov/vuln/api | All CVEs | | OSV.dev | api.osv.dev | npm, PyPI, Go, crates, Maven | | GitHub Advisory | github.com/advisories | npm, pip, composer, cargo | | Exa Search | Via MCP | Real-time web search |
Workflow
1. **Extract** dependencies from project (package.json, etc.) 2. **Query** each source for known CVEs 3. **Cross-reference** findings across sources 4. **Prioritize** by CVSS score and exploitability 5. **Report** with fix versions and workarounds
Query Strategy
For each dependency: 1. Search OSV.dev first (fastest, most accurate for packages) 2. Cross-check NVD for CVSS scoring 3. Use Exa for recent advisories not yet in databases 4. Check GitHub Advisory for maintainer responses
Severity Mapping
| CVSS Score | Severity | Action | |------------|----------|--------| | 9.0 - 10.0 | CRITICAL | Fix immediately | | 7.0 - 8.9 | HIGH | Fix before merge | | 4.0 - 6.9 | MEDIUM | Plan fix | | 0.1 - 3.9 | LOW | Document |
References
- [CVE APIs Reference](references/cve-apis.md)
- [Query Templates](references/templates/cve-query.md)
A plugin ecosystem that turns Claude Code into a supervised, multi-agent development environment.
Repo: fusengine/agents
Other skills on fusengine-agents.
- /agent-creator
Use when creating expert agents. Generates agent.md with frontmatter, hooks, required sections, and skill references.
Open skill - /apex-methodology
Use when starting ANY development task -- feature, bug fix, refactor, hotfix (triggers: implement, create, build, fix, add feature, refactor, develop).
Open skill - /brainstorming
Use when creating a feature/component or adding functionality. Fires BEFORE APEX Analyze to refine requirements via structured questioning.
Open skill - /challenge
Use before a root-cause, done/verified claim, irreversible action, or 2nd-time fix reaches the owner (APEX or plain conversation); also fires at every eLicit/Verify gate. Not for code correctness (use sniper).
Open skill - /code-quality
Use when validating code quality after modifications -- SOLID compliance, DRY duplication, linter errors, architecture violations. Do NOT use for functional verification (run verification FIRST, then code-quality).
Open skill - /elicitation
Use when an expert agent self-reviews and self-corrects code after the Execute phase, before sniper validation (BMAD-METHOD elicitation techniques).
Open skill

