apunkt/flakestorm
1
0
Fork 0
mirror of https://github.com/flakestorm/flakestorm.git synced 2026-04-26 01:06:26 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions
flakestorm/examples/broken_agent
History
Frank Humarang a36cecf255 Add initial project structure and configuration files 
- Created .gitignore to exclude unnecessary files and directories.
- Added Cargo.toml for Rust workspace configuration.
- Introduced example configuration file entropix.yaml.example for user customization.
- Included LICENSE file with Apache 2.0 license details.
- Created pyproject.toml for Python project metadata and dependencies.
- Added README.md with project overview and usage instructions.
- Implemented a broken agent example to demonstrate testing capabilities.
- Established Rust module structure with Cargo.toml and source files.
- Set up initial tests for assertions and configuration validation.
2025-12-28 21:55:01 +08:00
..
agent.py Add initial project structure and configuration files 2025-12-28 21:55:01 +08:00
README.md Add initial project structure and configuration files 2025-12-28 21:55:01 +08:00

README.md

Broken Agent Example

This example demonstrates a deliberately fragile AI agent that Entropix 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

cd examples/broken_agent
pip install fastapi uvicorn
uvicorn agent:app --port 8000

2. Run Entropix Against It

# From the project root
entropix run --config examples/broken_agent/entropix.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 Entropix to see your robustness score improve!