Unverified50% confidenceFactExact time
The three public threat intelligence sources—OpenPhish, PhishTank, and URLhaus—all operate on a model of crowdsourced reporting plus manual or automated review, and only URLs that have already been discovered, reported, and confirmed enter the database.
1
Sources
50%
Confidence
Long-term
Relevance
10/16/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedLLMs are vulnerable to prompt injection attacks, where malicious web pages or files can embed hidden instructions to induce AI to perform unintended actions.69% similarUnverifiedPeekray uses a two-tier architecture: it first queries three public threat lists—OpenPhish, PhishTank, and URLhaus—and if there is no hit, it then calls the Jev large model to make a decision.69% similarUnverifiedWhen using online APIs, query text and knowledge base fragments are processed through third-party platform servers, so scenarios involving trade secrets or personal privacy require careful compliance risk assessment.68% similarUnverifiedMultiple public cases in 2024 have demonstrated the feasibility of prompt injection attack vectors, including hijacking browser-controlling Agents via malicious web pages to execute fund transfers67% similarUnverifiedMalicious websites can embed hidden instructions in their pages to induce AI to perform unintended purchasing actions.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1049424API
curl https://kongchang.com/api/v1/knowledge/claims/1049424MCP
get_claim(id=1049424)