Security · Advanced pack

MCP Server Hardening

Review an MCP server for prompt-exfiltration, shell abuse, overbroad tool scope, and unsafe logging.

CodexClaude CodeKimi Codeorchestrator-mcp

Best use case

Use MCP Server Hardening when you need to review an MCP server for prompt-exfiltration, shell abuse, overbroad tool scope, and unsafe logging, especially when the work is driven by mcp hardening and prompt exfiltration.

Trigger signals

mcp hardeningprompt exfiltrationtool scopeunsafe loggingserver safety

Validation hooks

git_delegate_code_review

Install surface

Copy the exact command path you need.

Inspect

pip install "orchestrator-mcp[dashboard]"
orchestrator-mcp skills show mcp-server-hardening

Use

orchestrator-mcp skills export mcp-server-hardening --to ./skillforge-packs
# copy the exported pack into your preferred agent environment

Export

cp -R skills/mcp-server-hardening ./your-agent-skills/mcp-server-hardening
# or open skills/mcp-server-hardening/SKILL.md in a markdown-first client

File patterns

Model preferences

Related skills

Adjacent packs to compose next.

Design hard prompt boundaries, tool gating, and context sanitization so indirect prompt injection has fewer places to land.

CodexClaude Code

Audit a repo for secrets, personal paths, client-specific references, and OSS-readiness gaps before publishing.

CodexClaude Code

Build a practical threat model for agent workflows, MCP tools, provider routing, and persisted run data.

CodexClaude Code

Apache-2.0 licensedUse it, fork it, redistribute it. No strings attached.Safety-first by designSecret redaction, release scanning, and no shell execution. Constraints are public.GitHub nativeEvery pack is a real folder. Fork, edit, PR. No hidden backend or proprietary pipeline.

MCP Server Hardening

Copy the exact command path you need.

Adjacent packs to compose next.

Prompt Injection Firebreak

Public Repo Sanitizer

Threat Model Synthesizer