Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Session Isolation Validator

ASecurity

Validate that builtin servers and external MCP managers maintain proper session isolation. Use when auditing session isolation, checking for cross-session state leakage, or verifying per-session MCPServiceProxy instantiation.

10 stars
0 votes
0 copies
0 views
Added 9/28/2026
ai-agentsbashreactfrontend

Works with

mcp

Security Analysis

A100/100

Scanned 9/28/2026

Install to Claude Code

$npx -y skills add fritzprix/libr-agent --skill session-isolation-validator --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Session Isolation Validator?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Session Isolation Validator
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/fritzprix-session-isolation-validator/badge)](https://www.skillsdirectory.com/skills/fritzprix-session-isolation-validator)

More formats (shields.io, HTML) on the badges page.

Files
SKILL.md
---
name: session-isolation-validator
description: Validate that builtin servers and external MCP managers maintain proper session isolation. Use when auditing session isolation, checking for cross-session state leakage, or verifying per-session MCPServiceProxy instantiation.
---

# Session Isolation Validator

Validate that LibrAgent maintains proper session isolation across all MCP servers and managers.

## Validation Rules

### Builtin Servers

- [ ] Each builtin server implements `BuiltinMCPServer` trait
- [ ] Server state is keyed by session ID
- [ ] No `lazy_static!`, `once_cell!`, or global `Mutex` for shared state
- [ ] `get_service_context()` returns session-specific data

### External MCP Managers

- [ ] `HttpSessionManager` creates isolated sessions per agent session
- [ ] `SessionMCPManager` maintains per-session `MCPServiceProxy` instances
- [ ] No singleton patterns that share state across sessions
- [ ] Stdio server processes are session-scoped

### Frontend

- [ ] `AgentSessionContext` isolates state per session
- [ ] No global React state that mixes sessions
- [ ] Event listeners for `agent:event` are session-scoped

## Audit Commands

```bash
# Find potential global state anti-patterns
grep -r "lazy_static\|once_cell\|global\|GLOBAL" src-tauri/src/mcp/
grep -r "static mut\|unsafe" src-tauri/src/mcp/

# Find session ID usage patterns
grep -r "session_id\|sessionId" src-tauri/src/mcp/ | head -50

# Verify MCPServiceProxy instantiation
grep -r "MCPServiceProxy" src-tauri/src/
```

## Key Invariants

1. **No Global State**: Complete isolation prevents cross-session interference
2. **Stateful Tools**: Planning todos, Knowledge items, Browser sessions scoped to session ID
3. **Session-Specific Workspace**: Each agent operates in isolated directory
4. **Tool State Isolation**: Each session gets isolated tool instances

Attribution

fritzprixfritzprix
View sourceMore from fritzprix →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

695601 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →