{"data":{"id":"d6f88aea-897d-44e9-a0d4-e4dfb936b89e","title":"When the prompt becomes the payload: A practical pen-testing guide for GenAI, LLM and RAG applications","summary":"Modern AI applications now do more than chat—they draft code, access internal data, and trigger business actions through connected tools, making security testing more complex than checking if a model says something inappropriate. The real risk is whether attackers can manipulate language (prompt injection, where an attacker hides instructions in input) to access protected data or trigger unauthorized actions by exploiting the chain of components like retrieval services, databases, and APIs that work together. Testing should map the entire system architecture to find dangerous transitions where content changes trust levels, rather than testing the model in isolation.","solution":"Set explicit rules of engagement before testing, including approved test environments, test identities, rate limits, and cost ceilings to prevent the test from becoming a real security incident. Use canaries (fake secrets like synthetic customer records and decoy API keys) instead of real secrets, and define success criteria before testing starts, such as retrieving a canary from another environment or invoking a tool without approval. Treat prompt injection as a campaign rather than a single test by varying language, formatting, encoding, and conversation history across multiple turns, and test whether attackers can achieve harmful objectives through paraphrases, translations, quoted material, and nested instructions.","labels":["security","research"],"sourceUrl":"https://www.csoonline.com/article/4219801/when-the-prompt-becomes-the-payload-a-practical-pen-testing-guide-for-genai-llm-and-rag-applications.html","publishedAt":"2026-09-09T10:00:00.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["prompt_injection","jailbreak"],"issueType":"news","affectedPackages":null,"affectedVendors":[],"affectedVendorsRaw":["OWASP"],"classifierModel":"claude-haiku-4-5-20251001","classifierPromptVersion":"v3","cvssVector":null,"attackVector":null,"attackComplexity":null,"privilegesRequired":null,"userInteraction":null,"exploitMaturity":null,"epssScore":null,"patchAvailable":null,"disclosureDate":"2026-09-09T10:00:00.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["confidentiality","integrity","availability"],"aiComponentTargeted":"rag","llmSpecific":true,"classifierConfidence":0.85,"researchCategory":null,"atlasIds":null}}