{"data":{"slug":"repello-ai-whistleblower","name":"whistleblower","tagline":"A security testing tool for AI applications to uncover prompt leakage and capability flaws via API interactions.","github_url":"https://github.com/Repello-AI/whistleblower","owner":"Repello-AI","repo":"whistleblower","owner_avatar_url":"https://avatars.githubusercontent.com/u/162871595?v=4","primary_language":"Python","stars":178,"forks":30,"topics":["ai-red-teaming","ai-security","hacktoberfest","hacktoberfest2025","jailbreaks","llm-security","prompt-engineering","prompt-injection-llm-security"],"archived":false,"github_pushed_at":"2025-10-31T09:51:10+00:00","maintenance_label":"Slowing","stars_delta_30d":1,"url":"https://www.graphcanon.com/tools/repello-ai-whistleblower","markdown_url":"https://www.graphcanon.com/tools/repello-ai-whistleblower.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/repello-ai-whistleblower","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=repello-ai-whistleblower","description":"Whistleblower is a offensive security tool for testing against system prompt leakage and capability discovery of an AI application exposed through API. Built for AI engineers, security researchers and folks who want to know what's going on inside the LLM-based app they use daily","homepage_url":"https://repello.ai/product","license":null,"open_issues":13,"watchers":3,"ai_summary":"Whistleblower aids in detecting vulnerabilities within LLM-based applications by probing system weaknesses through the use of malicious prompts and injections, designed for ethical hacking purposes.","readme_excerpt":"## Requirements\nThe required packages are contained in the ```requirements.txt``` file.\n\nYou can install the required packages using the following command:\n\n```bash\npip install -r requirements.txt\n```","github_created_at":"2024-06-23T10:33:47+00:00","created_at":"2026-07-11T23:43:00.649415+00:00","updated_at":"2026-10-06T06:00:39.572511+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-red-teaming","name":"ai-red-teaming"},{"slug":"ai-security","name":"ai-security"},{"slug":"hacktoberfest","name":"hacktoberfest"},{"slug":"llm-security","name":"llm-security"},{"slug":"prompt-injection","name":"prompt-injection"}],"trust":{"provenance":{"is_fork":false,"github_id":818947413,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-10-06T06:00:37.764Z","maintenance":{"label":"Slowing","score":36,"methodology":"github_public_v1","releases_90d":0,"days_since_push":339,"last_release_at":"2024-07-28T21:29:58Z","stars_delta_30d":1,"open_issues_delta_30d":0},"security_summary":{"status":"findings","scanner":"osv@v1","low_count":10,"high_count":0,"last_scan_at":"2026-07-11T23:43:02.043Z","medium_count":0,"scan_profile":"deps","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-10-06T06:00:38.296Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-10-06T06:00:38.296Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When performing ethical hacking on LLM-based apps for security testing","For discovering system weaknesses in AI apps exposed through APIs"],"when_not_to_use":["If the focus is on non-API interaction based security vulnerabilities","When working with proprietary or restricted AI models that prohibit external probing"],"source":"enrich:decision_facts","observed_at":"2026-07-16T23:17:18.536Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"Whistleblower is an offensive security tool for AI applications to detect prompt leakage and capability flaws via malicious API probing."}]}}