By subimagesec
Operator workflows over the SubImage MCP server: triage findings, investigate CVEs, review attack paths, and audit cartography coverage. Requires a connected SubImage tenant.
Audit the current repo for cloud / SaaS providers that are NOT yet wired into SubImage, then check whether the SubImage compliance framework is enabled and surface its top actionable findings. Use when the user asks to "improve SubImage coverage", "what should I connect to SubImage", "audit cartography coverage", "what's missing in my SubImage setup", or runs this on a recurring schedule against their IaC repo. Closes the loop between "I have IaC defining X" and "SubImage tells me what's wrong with X".
Investigate a specific CVE in SubImage end-to-end (severity, KEV status, affected resources, fixability) and offer to pivot into attack-path exploration on the impacted assets. Use when the user mentions a CVE id ("CVE-2024-3094", "what's affected by CVE-2023-44487"), asks to "investigate this CVE", "is this CVE exploitable in our environment", "should we patch this", or hands off a vendor advisory. Always finishes by asking whether to chain into review-attack-path.
Walk a SubImage attack path step by step, identify the most sensitive impacted assets, propose the fastest remediation, hunt for credible n+1 extensions the engine has not yet modeled, and optionally simulate what-if scenarios. Use when the user asks to "review this attack path", "explain this attack path", "what would happen if X is compromised", "what attack paths involve <asset>", "find lateral movement opportunities from <asset>", "assess the blast radius of <asset>", or pivots from `subimage-mcp:investigate-cve`. Three entry modes: by path id, by asset id, or n+1 extension hunt.
Triage SubImage security findings against the enabled compliance frameworks, group them by theme, and recommend the next investigation steps. Use when the user asks to "triage findings", "what's new in SubImage today", "summarize my open findings", "any urgent findings", or wants a daily/weekly findings digest. Pulls framework status first, then per-framework rules and findings, and proposes the highest-priority items per framework.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Claude Code marketplace for SubImage, the cloud-native security platform.
Two plugins ship from this repo:
subimage-setup : onboarding recipes for cloud and SaaS data sources (AWS, GCP, Azure, GitHub, Kubernetes outpost). Terraform / CloudFormation / Helm / aws-cli / gcloud / az / gh paths. Designed to run inside an IaC or scripts repo.subimage-mcp : operator workflows over the SubImage MCP server (triage findings, investigate CVEs, review attack paths, audit cartography coverage). Designed to run alongside an authenticated SubImage tenant.The two are independent; install whichever your workflow needs.
claude plugin marketplace add subimagesec/skills
claude plugin install subimage-setup@subimage
claude plugin install subimage-mcp@subimage
After install, skills are namespaced under their plugin:
/subimage-setup:connect-aws
/subimage-setup:connect-gcp
/subimage-setup:connect-azure
/subimage-setup:connect-kubernetes-outpost
/subimage-setup:connect-github
/subimage-mcp:triage-new-findings
/subimage-mcp:investigate-cve
/subimage-mcp:review-attack-path
/subimage-mcp:improve-cartography-coverage
Most are model-invocable: the agent picks them up automatically from the description when the user phrasing matches. You can also call any of them by name as a slash command.
subimage-mcp skills assume the SubImage MCP server is connected. Set that up first: https://app.subimage.io/docs/agents/connect_via_mcp
subimage-setup skills run anywhere a shell or IaC repo lives; no SubImage tenant connection is required to generate the IaC code (only to verify it afterwards).
.claude-plugin/
marketplace.json # marketplace catalog
plugins/
subimage-setup/
.claude-plugin/plugin.json # plugin manifest
skills/
connect-aws/SKILL.md
connect-gcp/SKILL.md
connect-azure/SKILL.md
connect-kubernetes-outpost/SKILL.md
connect-github/SKILL.md
subimage-mcp/
.claude-plugin/plugin.json
skills/
triage-new-findings/SKILL.md
investigate-cve/SKILL.md
review-attack-path/SKILL.md
improve-cartography-coverage/SKILL.md
Each SKILL.md follows the Anthropic skill convention and the Claude Code plugin spec. When adding or editing a skill:
name (matches the directory) and description (when-to-trigger sentence with concrete user-typed phrasings).{{...}} placeholder. Use <NAMED_VAR> and instruct the agent to ask the user for the value if it is not yet known.—) in any markdown. Use :, ;, ,, or parentheses.SKILL.md. If a skill exceeds it, split detailed reference material into a references/ subdirectory and tell the agent when to load it.MIT. See LICENSE.
npx claudepluginhub subimagesec/skills --plugin subimage-mcpOnboard cloud and SaaS data sources into SubImage from your IaC or CLI environment (AWS, GCP, Azure, GitHub, Kubernetes outpost). Terraform / CloudFormation / Helm / aws-cli / gcloud / az / gh paths.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Plugin-safe Claude Code distribution of Antigravity Awesome Skills with 1,561 supported skills.
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer