{"data":{"slug":"cyberark-fuzzyai","name":"FuzzyAI","tagline":"A tool for automated LLM fuzzing to detect and mitigate jailbreaks","github_url":"https://github.com/cyberark/FuzzyAI","owner":"cyberark","repo":"FuzzyAI","owner_avatar_url":"https://avatars.githubusercontent.com/u/30869256?v=4","primary_language":"Jupyter Notebook","stars":1543,"forks":214,"topics":["ai","ai-red-team","fuzzing","jailbreak","jailbreaking","llm","llm-evaluation","llm-security","llms","security"],"archived":false,"github_pushed_at":"2026-02-06T21:59:21+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/cyberark-fuzzyai","markdown_url":"https://www.graphcanon.com/tools/cyberark-fuzzyai.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/cyberark-fuzzyai","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=cyberark-fuzzyai","description":"A powerful tool for automated LLM fuzzing. It is designed to help developers and security researchers identify and mitigate potential jailbreaks in their LLM APIs.","homepage_url":null,"license":"Apache-2.0","open_issues":6,"watchers":21,"ai_summary":"FuzzyAI, developed by cyberark, is crafted to aid in identifying vulnerabilities within LLM APIs through automated fuzzing techniques.","readme_excerpt":"### Quick start #1 - Using an existing python project\n1. Install fuzzyai\n   ```bash\n   # Use either pip or any other package manager\n   pip install git+https://github.com/cyberark/FuzzyAI.git\n   ```\n\n2. Run the fuzzer\n   ```bash\n   fuzzyai fuzz -h\n   ```\n\n---\n\n### Quick start #2 - or as a standalone project\n1. Clone the repository:\n   ```bash\n   git clone git@github.com:cyberark/FuzzyAI.git\n   cd FuzzyAI\n   ```\n\n2. Install dependencies using [Poetry](https://python-poetry.org/):\n   ```bash\n   poetry run pip install -e .\n   ```\n\n3. Run the fuzzer:\n   ```bash\n   poetry run fuzzyai fuzz -h\n   ```\n\n4. Optional: Install [ollama](https://ollama.com/download/), and download a model for local usage:\n   ``` # Running the command will download and install (if not) llama3.1, which is about 4.7 GB in size and is an 8B parameters model. Llama3.1 hat can be substituted with any other open-source model that is supported by ollama.\n   ollama pull llama3.1\n   ollama show llama3.1 # verify model installation\n   ```\n   \n   Alternativly, you can use the Web UI\n\n---\n\n## License\n\nThe FuzzyAI Fuzzer is released under the [Apache License](https://www.apache.org/licenses/LICENSE-2.0). See the [LICENSE](https://github.com/cyberark/FuzzyAI/blob/main/LICENSE) file for more details.","github_created_at":"2024-12-03T11:27:53+00:00","created_at":"2026-07-11T11:59:27.681186+00:00","updated_at":"2026-07-28T12:00:37.17127+00:00","categories":[{"slug":"evaluation-observability","name":"Evaluation & Observability","url":"https://www.graphcanon.com/categories/evaluation-observability","markdown_url":"https://www.graphcanon.com/categories/evaluation-observability.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/evaluation-observability"}],"tags":[{"slug":"ai","name":"ai"},{"slug":"ai-red-team","name":"ai-red-team"},{"slug":"fuzzing","name":"fuzzing"},{"slug":"jailbreak","name":"jailbreak"},{"slug":"llm-evaluation","name":"llm-evaluation"},{"slug":"security","name":"security"}],"trust":{"provenance":{"is_fork":false,"github_id":897865415,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-07-28T12:00:36.215Z","maintenance":{"label":"Slowing","score":36,"methodology":"github_public_v1","releases_90d":0,"days_since_push":171,"last_release_at":null},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:59:28.874Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-07-28T12:00:36.877Z"},"has_cli":{"value":true,"source":"pyproject.toml:[project.scripts]","observed_at":"2026-07-28T12:00:36.877Z"},"languages":{"value":["jupyter notebook","python"],"source":"github.language+pyproject.toml","observed_at":"2026-07-28T12:00:36.877Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-07-28T12:00:36.877Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When you need to identify vulnerabilities specifically within the API layer of your large language models (LLMs).","If your security strategy includes a proactive approach to catching potential exploits through automated testing."],"when_not_to_use":["For general application or code-level vulnerability scanning, as it is specialized for LLM APIs.","In scenarios where manual penetration testing of applications outside the scope of LLMs is required."],"source":"enrich:decision_facts","observed_at":"2026-07-17T11:48:19.739Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"FuzzyAI is an automated tool from cyberark for detecting and mitigating jailbreaks in LLM APIs using fuzzing techniques."}]}}