# Prompt Injection Detector

> Prompt injection detection and prevention for secure LLM applications

- Skill: `a5c-ai/prompt-injection-detector` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add a5c-ai/prompt-injection-detector`
- Raw SKILL.md: https://api.skillmd.com/api/skills/a5c-ai/prompt-injection-detector/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: a5c-ai (https://skillmd.com/u/a5c-ai)
- Updated: 2026-09-09
- Page: https://skillmd.com/skills/a5c-ai/prompt-injection-detector

---


# Prompt Injection Detector Skill

## Capabilities

- Detect prompt injection attempts
- Implement input sanitization
- Configure detection classifiers
- Design defense layers
- Implement canary token detection
- Create injection logging and alerting

## Target Processes

- prompt-injection-defense
- tool-safety-validation

## Implementation Details

### Detection Methods

1. **Pattern Matching**: Known injection patterns
2. **ML Classifiers**: Trained injection detectors
3. **Canary Tokens**: Detect instruction override
4. **LLM-Based**: Use LLM to detect manipulation
5. **Perplexity Analysis**: Unusual input patterns

### Defense Strategies

- Input preprocessing
- Prompt structure design
- Output validation
- Sandboxed execution
- Multi-layer defense

### Configuration Options

- Detection threshold
- Pattern rules
- Classifier model
- Action policies
- Alerting settings

### Best Practices

- Defense in depth
- Regular pattern updates
- Monitor false positives
- Test with red-team inputs

### Dependencies

- rebuff (optional)
- transformers
- Custom classifiers