SkillForge

Appearance

Get Started

Security · Advanced pack

Prompt Injection Firebreak

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

CodexClaude CodeKimi Codeorchestrator-mcp
Open pack on GitHubBack to catalog

Best use case

Use Prompt Injection Firebreak when you need to design hard prompt boundaries, tool gating, and context sanitization so indirect prompt injection has fewer places to land, especially when the work is driven by prompt injection and context sanitization.

Trigger signals

prompt injectioncontext sanitizationtool gatingagent security

Validation hooks

verify_prompt_boundarygit_delegate_code_review

Install surface

Copy the exact command path you need.

Inspect

pip install "orchestrator-mcp[dashboard]"
orchestrator-mcp skills show prompt-injection-firebreak

Use

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

Export

cp -R skills/prompt-injection-firebreak ./your-agent-skills/prompt-injection-firebreak
# or open skills/prompt-injection-firebreak/SKILL.md in a markdown-first client

File patterns

**/prompts/****/tools/****/*.md**/*.yaml

Model preferences

Related skills

Adjacent packs to compose next.

SecurityAdvanced pack

Public Repo Sanitizer

Open pack

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

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.