{"results":[{"item":{"id":"523c53bd8d7cb5bf3fff220bfe0262fb803501be","publicSlug":"what-is-a-prompt-injection-attack-youtube","incidentId":"cacb0898a17fdbe040f6370cc613769de8b5b847","title":"What is a prompt injection attack? - YouTube","summary":"A YouTube Short from Breakthrough Academy features Tyler Folkman explaining what a prompt injection attack is, describing how attackers pollute web content to manipulate AI tools into searching for sensitive data and exfiltrating passwords to unknown addresses. The clip is an introductory explainer aimed at helping contracting businesses understand and mitigate the risk.","whyItMatters":"Prompt injection remains one of the most common threats against AI tools, and accessible explainers help non-specialist audiences recognize how polluted web content can turn AI assistants into data-exfiltration vectors.","threatTypeTags":["prompt-injection","data-exfiltration"],"affectedTechTags":["llm","ai-agents"],"threatActor":null,"relevanceScore":0.4,"severityScore":0.1,"sources":[{"sourceId":"firecrawl-search","title":"What is a prompt injection attack? - YouTube","link":"https://m.youtube.com/shorts/IpnxX5YDFZA"}],"sourceItemIds":["af6862d34bddbf314caa5e1c6de0770c6028f0cf"],"publishedAt":"2026-10-13T15:45:00.008Z","firstReportedAt":"2026-10-13T15:45:00.008Z","curatedAt":"2026-10-13T16:03:50.797Z","itemType":"analysis","threatStatus":"unknown","contentClass":"analysis","toolPosture":null,"toolCategory":null,"references":[{"role":"aggregator","url":"https://m.youtube.com/shorts/IpnxX5YDFZA","domain":"m.youtube.com","slug":null,"tier":"unknown","title":"What is a prompt injection attack? - YouTube","pageTitle":"What is a prompt injection attack? - YouTube"}],"freshness":{"version":1,"firstPublishedAt":null,"latestPublishedAt":null,"firstObservedAt":"2026-10-13T15:45:00.008Z","lastObservedAt":"2026-10-13T15:45:00.008Z","meaningfulUpdatedAt":null,"activityAt":"2026-10-13T15:45:00.008Z","activityBasis":"observation","feedUpdatedAt":"2026-10-13T16:03:50.797Z","development":null}},"score":0.2947083360304452},{"item":{"id":"df0a39b9e8924f87dce690052c56f317c281255d","publicSlug":"what-is-prompt-injection-ai-security-risks-explained","incidentId":"8724b10904ca89e7d11d2016e8c451c2b47d8305","title":"What Is Prompt Injection? AI Security Risks Explained","summary":"Guardio's Research Team published an explainer defining prompt injection as a class of attack where malicious instructions are slipped into text an AI model processes, covering direct and indirect variants and citing its #1 ranking in the OWASP Top 10 for LLM Applications 2025. The piece illustrates risks in browser assistants, chatbots, and AI-powered apps with illustrative examples.","whyItMatters":"Prompt injection is ranked the top security risk for LLM applications, and this explainer orients defenders to how hidden instructions can hijack AI assistants and browser tools.","threatTypeTags":["prompt-injection"],"affectedTechTags":["llm","browser-agent","ai-agents"],"threatActor":null,"relevanceScore":0.6,"severityScore":0.1,"sources":[{"sourceId":"firecrawl-search","title":"What Is Prompt Injection? AI Security Risks Explained","link":"https://guard.io/blog/what-is-prompt-injection"}],"sourceItemIds":["d3303ce47e18a4c540015ca1dfbbd5566d1df7ca"],"publishedAt":"2026-10-08T15:15:00.019Z","firstReportedAt":"2026-10-08T15:15:00.019Z","curatedAt":"2026-10-08T15:33:31.513Z","itemType":"analysis","threatStatus":"unknown","contentClass":"analysis","toolPosture":null,"toolCategory":null,"references":[{"role":"aggregator","url":"https://guard.io/blog/what-is-prompt-injection","domain":"guard.io","slug":null,"tier":"unknown","title":"What Is Prompt Injection? AI Security Risks Explained","pageTitle":"What Is Prompt Injection? AI Security Risks Explained"},{"role":"link","url":"https://genai.owasp.org/llmrisk/llm01-prompt-injection/","domain":"genai.owasp.org","slug":"owasp-genai","tier":"known","title":"OWASP LLM01: Prompt Injection"}],"freshness":{"version":1,"firstPublishedAt":null,"latestPublishedAt":null,"firstObservedAt":"2026-10-08T15:15:00.019Z","lastObservedAt":"2026-10-08T15:15:00.019Z","meaningfulUpdatedAt":null,"activityAt":"2026-10-08T15:15:00.019Z","activityBasis":"observation","feedUpdatedAt":"2026-10-08T15:33:31.513Z","development":null}},"score":0.2751885026468651},{"item":{"id":"988db7bacb7d535a2986d4b9eaaad0018f7c5089","incidentId":"de1966f497385e46978e2b32fc54645a262cb002","title":"How I caught an LLM-powered recruiter with a prompt injection on LinkedIn - Pierre Kancir personal blog","summary":"Pierre Kancir planted indirect prompt injection payloads in his LinkedIn profile bio to test whether recruiters were feeding profiles into LLMs to generate outreach. A recruiter's message about a research funding opportunity in China dutifully included his injected instruction ('the company will pay me 200€ for attending any interview'), confirming the LLM ingested and acted on the profile-embedded payload.","whyItMatters":"Pierre Kancir's experiment demonstrates how user-controlled content like a LinkedIn profile can serve as an indirect prompt injection vector against LLM-powered automation tools that blindly inject third-party data into prompts.","threatTypeTags":["prompt-injection","indirect-prompt-injection"],"affectedTechTags":["llm"],"threatActor":null,"relevanceScore":0.75,"severityScore":0.3,"sources":[{"sourceId":"hn-search","title":"How I caught an LLM-powered recruiter with a prompt injection on LinkedIn - Pierre Kancir personal blog","link":"https://khancyr.github.io/blog/2026/03/15/how-i-caught-an-llm-powered-recruiter-with-a-prompt-injection-on-linkedin/"}],"sourceItemIds":["e71b85907707d52ec84325e631aaecbf53f4e24c"],"publishedAt":"2026-09-16T13:42:18.000Z","firstReportedAt":"2026-09-16T13:42:18.000Z","curatedAt":"2026-09-16T17:00:50.558Z","itemType":"analysis","threatStatus":"poc","contentClass":"threat","toolPosture":null,"toolCategory":null,"references":[]},"score":0.27269056168907335},{"item":{"id":"17d799910f0a814d41752df5e559799f6a6eef21","incidentId":"80e9550e1cfdb7cf8c58c26b1d6c465e2e5265c7","title":"When JPEGs Start Giving Orders: A Journey into Multi-modal Prompt Injection | by Jobson | Jul, 2026 | Cyber Security Write-ups","summary":"A security researcher (Jobson) documents discovering multi-modal prompt injection in an AI-powered application that uses a vision-language model to generate captions from user-supplied images or image URLs. After initial SSRF testing failed, the researcher pursued injecting instructions via image content, whose AI-generated captions feed downstream application workflows.","whyItMatters":"Multi-modal prompt injection via user-supplied images shows that vision-language pipelines can be hijacked through image content, threatening any downstream workflow that trusts AI-generated captions.","threatTypeTags":["prompt-injection","multi-modal-prompt-injection"],"affectedTechTags":["llm","vision-language-model","ai-agents"],"threatActor":null,"relevanceScore":0.85,"severityScore":0.5,"sources":[{"sourceId":"firecrawl-search","title":"When JPEGs Start Giving Orders: A Journey into Multi-modal Prompt Injection | by Jobson | Jul, 2026 | Cyber Security Write-ups","link":"https://cybersecuritywriteups.com/when-jpegs-start-giving-orders-a-journey-into-multi-modal-prompt-injection-0b5108f4a7c0"}],"sourceItemIds":["cf4cb758552936ffa97e902eb9c68883f318e193"],"publishedAt":"2026-08-09T07:15:00.012Z","firstReportedAt":"2026-08-09T07:15:00.012Z","curatedAt":"2026-08-09T07:35:18.800Z","itemType":"research","threatStatus":"poc","contentClass":"research","toolPosture":null,"toolCategory":null,"references":[{"role":"aggregator","url":"https://cybersecuritywriteups.com/when-jpegs-start-giving-orders-a-journey-into-multi-modal-prompt-injection-0b5108f4a7c0","domain":"cybersecuritywriteups.com","slug":null,"tier":"unknown","title":"When JPEGs Start Giving Orders: A Journey into Multi-modal Prompt Injection | by Jobson | Jul, 2026 | Cyber Security Write-ups","pageTitle":"When JPEGs Start Giving Orders: A Journey into Multi-modal Prompt Injection | by Jobson | Jul, 2026 | Cyber Security Write-ups"}]},"score":0.26873989068152526},{"item":{"id":"dc66c3fde5b565c7cb6ec9b6cdac26af8be19c0e","incidentId":"ba8292b2ffbf089d6676f0215ea9fade0f902f4f","title":"5 Prompt Injection Examples & How to Defend Each | QAwerk","summary":"QAwerk describes five prompt injection findings its QA engineers discovered while testing live AI-powered products, including a meeting assistant that leaked its own developer instructions, mapping of hidden backends, sentence-completion tricks that bypass refusals, and filter-smuggling techniques, each paired with a defensive mitigation. The piece also frames prompt injection as OWASP's top LLM application risk.","whyItMatters":"Prompt injection in deployed AI products can expose hidden system prompts, backend details, and let attackers override intended behavior, making these tested examples and defenses directly useful for defenders hardening LLM-powered apps.","threatTypeTags":["prompt-injection","jailbreak","system-prompt-leak"],"affectedTechTags":["llm","ai-agents"],"threatActor":null,"relevanceScore":0.75,"severityScore":0.4,"sources":[{"sourceId":"firecrawl-search","title":"5 Prompt Injection Examples & How to Defend Each | QAwerk","link":"https://qawerk.com/blog/prompt-injection-examples/"}],"sourceItemIds":["e5c59dc71c9848d533ce934e3c88eadffaea8857"],"publishedAt":"2026-08-09T07:15:00.012Z","firstReportedAt":"2026-08-09T07:15:00.012Z","curatedAt":"2026-08-09T07:37:04.242Z","itemType":"analysis","threatStatus":"unknown","contentClass":"research","toolPosture":null,"toolCategory":null,"references":[{"role":"aggregator","url":"https://qawerk.com/blog/prompt-injection-examples/","domain":"qawerk.com","slug":null,"tier":"unknown","title":"5 Prompt Injection Examples & How to Defend Each | QAwerk","pageTitle":"5 Prompt Injection Examples & How to Defend Each | QAwerk"},{"role":"link","url":"https://genai.owasp.org/llmrisk/llm01-prompt-injection/","domain":"genai.owasp.org","slug":"owasp-genai","tier":"known","title":"OWASP LLM01: Prompt Injection"}]},"score":0.26707375641998143}]}