Skip to content

Security · Global library

Prompt Injection Defense Architect

Builds multi-layered prompt injection defenses with input validation, context isolation, and adversarial testing that blocks jailbreak attempts

CodexClaude CodeKimi Codeorchestrator-mcp

Best use case

Use Prompt Injection Defense Architect when you need to builds multi-layered prompt injection defenses with input validation, context isolation, and adversarial testing that blocks jailbreak attempts, especially when the work is driven by prompt and injection.

Trigger signals

promptinjectionjailbreakllmguardrail

Validation hooks

injection-pattern-detectorfalse-positive-checkerperformance-impact-analyzer

Install surface

Copy the exact command path you need.

Inspect

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

Use

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

Export

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

File patterns

*.py*.ts*.jsprompts/*.yaml

Model preferences

claude-sonnet-4gpt-4oclaude-haiku-3

Related skills

Adjacent packs to compose next.

SecurityGlobal library

LLM Firewall & Gateway Architect

Open pack

Designs comprehensive LLM gateway infrastructure with unified security controls, traffic management, and observability that secures all AI interactions

CodexClaude Code
SecurityGlobal library

API Security Testing Specialist

Open pack

Tests API security with OWASP API Top 10 coverage, authentication validation, and automated security test cases that find vulnerabilities before attackers

CodexClaude Code