最近 7 天
0
次命中
Keyword Tracking
关键词追踪：indirect prompt injection
这个页面会长期追踪你配置里关心的关键词，并把命中的论文按日期沉淀下来。
最近 30 天
3
次命中
全部历史
6
次命中
近期走势
最近一次命中来自 Agent Runtime Security：CodeSentinel: A Three-Layer Defense Against Indirect Prompt Injection in Code Contexts
2026-06-15
0
2026-06-16
0
2026-06-17
0
2026-06-18
1
2026-06-19
0
2026-06-20
0
2026-06-21
0
2026-06-22
0
2026-06-23
0
2026-06-24
0
2026-06-25
0
2026-06-26
0
2026-06-27
0
2026-06-28
0
命中明细
按日期回看匹配到这个关键词的论文标题，并保留来源 feed 信息。
2026-06-18
CodeSentinel: A Three-Layer Defense Against Indirect Prompt Injection in Code Contexts
Code large language models increasingly retrieve external code context from repositories, documentation, issue threads, and coding-agent environments, creating an indirect prompt-…
2026-06-04
Caught in the Act(ivation): Toward Pre-Output and Multi-Turn Detection of Credential Exfiltration by LLM Agents
LLM agents often place sensitive credentials in the same context window as untrusted retrieved content, creating a direct path for indirect prompt injection to induce credential e…
2026-06-02
AgentRedBench: Dynamic Redteaming and Integration-Aware Defense for LLM Agents over SaaS Integrations
Indirect prompt injection in tool-use agents is a concrete production threat: LLM agents read from integrations (third-party services such as Gmail, Salesforce, or Jira accessed t…
2026-05-19
An Empirical Study of Privacy Leakage Chains via Prompt Injection in Black-Box Chatbot Environments
LLM-based chatbot agents increasingly process user requests by combining natural-language reasoning with external tools such as web browsing. These capabilities improve usability,…
2026-05-08
Constraining Host-Level Abuse in Self-Hosted Computer-Use Agents via TEE-Backed Isolation
Self-hosted computer-use agents (SHCUAs), such as OpenClaw, combine natural-language interaction with direct access to host-side resources, including browsers, files, scripts, sys…
2026-04-14
ClawGuard: A Runtime Security Framework for Tool-Augmented LLM Agents Against Indirect Prompt Injection
Tool-augmented Large Language Model (LLM) agents have demonstrated impressive capabilities in automating complex, multi-step real-world tasks, yet remain vulnerable to indirect pr…