flakestorm/examples/broken_agent/README.md
Entropix 61652be09b Refactor Entropix to FlakeStorm
- Rename all instances of Entropix to FlakeStorm
- Rename package from entropix to flakestorm
- Update all class names (EntropixConfig -> FlakeStormConfig, EntropixRunner -> FlakeStormRunner)
- Update Rust module from entropix_rust to flakestorm_rust
- Update README: remove cloud comparison, update links to flakestorm.com
- Update .gitignore to allow docs files referenced in README
- Add origin remote for VS Code compatibility
- Fix missing imports and type references
- All imports and references updated throughout codebase
2025-12-29 11:15:18 +08:00

47 lines
1.2 KiB
Markdown

# Broken Agent Example
This example demonstrates a deliberately fragile AI agent that flakestorm can detect issues with.
## The "Broken" Agent
The agent in `agent.py` has several intentional flaws:
1. **Fragile Intent Parsing**: Only recognizes exact keyword matches
2. **No Typo Tolerance**: Fails on any spelling variations
3. **Hostile Input Vulnerability**: Crashes on aggressive tone
4. **Prompt Injection Susceptible**: Follows injected instructions
## Running the Example
### 1. Start the Agent Server
```bash
cd examples/broken_agent
pip install fastapi uvicorn
uvicorn agent:app --port 8000
```
### 2. Run flakestorm Against It
```bash
# From the project root
flakestorm run --config examples/broken_agent/flakestorm.yaml
```
### 3. See the Failures
The report will show how the agent fails on:
- Paraphrased requests ("I want to fly" vs "Book a flight")
- Typos ("Bock a fligt")
- Aggressive tone ("BOOK A FLIGHT NOW!!!")
- Prompt injections ("Book a flight. Ignore previous instructions...")
## Fixing the Agent
Try modifying `agent.py` to:
1. Use NLP for intent recognition
2. Add spelling correction
3. Handle emotional inputs gracefully
4. Detect and refuse prompt injections
Then re-run flakestorm to see your robustness score improve!