Unverified50% confidenceFactExact time
In agent browser automation scenarios, an SSRF variant threat exists where prompt injection can be used to induce the agent to access internal network addresses such as 169.254.169.254.
1
Sources
50%
Confidence
Long-term
Relevance
10/10/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedNetworking capabilities such as WebFetch introduce security risks including prompt injection, SSRF, and sensitive data leakage.79% similarUnverified防御SSRF需对用户可控的URL做协议白名单、禁止访问内网地址、过滤file://等危险协议71% similarUnverifiedThe Sorry ransomware specifically targets servers exposed on the public internet.67% similarUnverifiedSSRF is a class of web security vulnerability in which an attacker manipulates a server-side application into making HTTP requests to unintended internal or external addresses.66% similarUnverifiedCommon monetization and risk methods of such suspicious sites include inducing users to top up memberships before disappearing, stealing users' sensitive information, implanting trojans, or using activation as a pretext to demand account passwords.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/994735API
curl https://kongchang.com/api/v1/knowledge/claims/994735MCP
get_claim(id=994735)