ai-ml-attacks
This skill should be used when the user asks about "AI security", "ML pipeline attacks", "prompt injection", "model…
@allsmogInstall SkillSecurity
Skill
/scope-repo
Decide audit boundaries for large or monorepo targets and write audit-plan.md.
Claude Code
$ npx -y skills add allsmog/vuln-scout --skill scope-repo --agent claude-code
Codex
$ npx skills add allsmog/vuln-scout --skill scope-repo -a codex -y
Cursor
$ npx skills add allsmog/vuln-scout --skill scope-repo -a cursor -y
Gemini CLI
$ npx skills add allsmog/vuln-scout --skill scope-repo -a gemini-cli -y
GitHub Copilot
$ npx skills add allsmog/vuln-scout --skill scope-repo -a github-copilot -y
OpenCode
$ npx skills add allsmog/vuln-scout --skill scope-repo -a opencode -y
Windsurf
$ npx skills add allsmog/vuln-scout --skill scope-repo -a windsurf -y
SKILL.md
scope-repo.SKILL.mdname: scope-repo description: Decide audit boundaries for large or monorepo targets and write audit-plan.md.
Scope Repo
Use this task skill when the user asks to scope this repo, decide where to focus, decide what to audit first, or handle a large codebase.
Workflow
1. Trigger `large-codebase-check` when repository size or monorepo structure is unclear. 2. Run `/vuln-scout:scope --list` for workspace discovery when applicable. 3. Run `/vuln-scout:scope <path> --compress --name <scope-name>` for the selected boundary. 4. Call `app-mapper` to produce `.claude/app-understanding.md`. 5. Write or update `.claude/audit-plan.md` with scope name, workspace list, entry points, trust boundaries, and high-risk modules.
Produces
- `.claude/audit-plan.md`
- workspace list
- scope name
When NOT To Trigger
Do not trigger for STRIDE-only modeling, dangerous-function lookup, framework pattern questions, or vulnerability-specific education unless the user asks for audit scoping.
Ships withvuln-scout
AI-powered whitebox penetration testing plugin for Claude Code. 9 languages, 22 skills, 7 autonomous agents. STRIDE threat modeling, OWASP 2025 coverage, polyglot monorepo support.
2635 skills9 agents
Stars on GitHub
Momentum
- stars in total
- 26
Other skills on vuln-scout.
@allsmogInstall Skillbusiness-logic
This skill should be used when the user asks about "business logic", "workflow vulnerability", "trust boundary", "state machine",…
@allsmogInstall Skillcache-poisoning
This skill should be used when the user asks about "cache poisoning", "web cache deception", "CDN cache", "proxy cache", "nginx…
@allsmogInstall Skillcloud-native
This skill should be used when the user asks about "cloud security", "AWS security", "GCP security", "Azure security",…
@allsmogInstall Skillcompliance-mapping
This skill should be used when the user asks about "compliance mapping", "PCI-DSS", "HIPAA", "SOC 2", "NIST CSF", "regulatory…
@allsmogInstall Skillcpg-analysis
This skill should be used when the user asks about "Code Property Graph", "CPG analysis", "Joern queries", "CPGQL", "data flow…
@allsmogInstall SkillMore skills from other plugins.
api-security
Use for authorized security assessment of REST, GraphQL, WebSocket, or SOAP APIs, including discovery, authentication,…
@zhaoxuya520Install Skillabusing-dpapi-for-cred…
Extract and decrypt Windows DPAPI-protected secrets (Credential Manager, browser logins/cookies, Wi-Fi credentials, KeePass keys)…
@mukul975Install Skillclean-user-facing-text
Clean and finalize authorized natural-language text intended for readers by auditing suspicious invisible Unicode and rewriting…
@guillaumemeyerInstall Skill
Questions about scope-repo.
- Which coding agents can use scope-repo?
- scope-repo installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.