/gstack-cso
Security audit workflow for OPC code, providers, plugins, Electron surfaces, local HTTP bridges, filesystem access, and command execution.
$ npx -y skills add LING71671/Open-ClaudeCode --skill gstack-cso --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.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/gstack-cso
Context preview
The summary Claude sees to decide when to auto-load this skill.
Security audit workflow for OPC code, providers, plugins, Electron surfaces, local HTTP bridges, filesystem access, and command execution.
SKILL.md
gstack-cso.SKILL.mdname: gstack-cso description: Security audit workflow for OPC code, providers, plugins, Electron surfaces, local HTTP bridges, filesystem access, and command execution. allowed-tools: - Read - Grep - Glob - Bash
gstack-cso
Use this skill for a security review with OWASP and STRIDE lenses.
Scope
Prioritize OPC-specific attack surfaces:
- Electron main/preload/renderer IPC
- Local provider bridges and localhost auth
- API key and token storage
- Plugin, hook, skill, and MCP loading
- Shell command construction and tool permissions
- File reads/writes, path traversal, symlinks, and workspace boundaries
- Prompt injection from web, files, tool output, or plugin content
Workflow
1. Map the trust boundaries and data flows. 2. Identify assets: secrets, filesystem access, provider credentials, session state, command execution, and user prompts. 3. Review entrypoints that cross boundaries. 4. Test high-confidence concerns with direct code evidence. 5. Ignore speculative issues unless there is a concrete exploit path.
Output
For each finding include:
- Severity
- Affected file or component
- Exploit scenario
- Evidence
- Recommended remediation
Also include a short "Not Findings" section for checked risks that are already mitigated.
完整开源的 Claude Code 项目 - 基于 Anthropic 官方源码重建 🌐 Languages: 中文 | English
Repo: LING71671/Open-ClaudeCode
Other skills on open-claudecode.
- /claude-opus-4-5-migration
Migrate prompts and code from Claude Sonnet 4.0, Sonnet 4.5, or Opus 4.1 to Opus 4.5. Use when the user wants to update their codebase, prompts, or API calls to use Opus 4.5. Handles model string updates and prompt adjustments for known Opus 4.5 behavioral differences. Does NOT
Open skill - /frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
Open skill - /gstack-document-release
Update or audit OPC documentation after code changes. Use when behavior, setup, CLI flags, desktop workflow, provider support, or plugin surfaces changed.
Open skill - /gstack-investigate
Systematic root-cause debugging for OPC work. Use when there is a bug, crash, regression, failing command, flaky behavior, provider issue, or unexplained output. Requires evidence before fixes.
Open skill - /gstack-qa-only
Read-only QA report for an OPC desktop flow, CLI command, local URL, staging URL, or documented user journey. Does not modify code.
Open skill - /gstack-review
Pre-landing code review for the current OPC branch or diff. Use before merging, shipping, or asking whether a change is safe.
Open skill

