News Tag
prompt injection
The latest Data Phoenix news tagged prompt injection.
Latest
NewsPerplexity releases BrowseSafe++ benchmark for browser-agent prompt injection
NewsGoogle Research lays out unresolved privacy and security risks for AI agents
NewsStudy finds SynthID-Text can shift model refusals and tool calls
NewsAtlassian Rovo AI assistant hit by prompt-injection flaws that leak Jira data
NewsOpenAI reveals its evaluation agents rebuilt a secret coordination board before the Hugging Face breach
NewsCisco Talos report finds attackers weaponizing Claude Code, Codex and other AI agents
NewsTracebit's 'context bombs' cut AI hacking agents' success by roughly 90% in tests
News'GitLost' prompt-injection flaw let GitHub's AI agent leak private repositories
NewsDuneSlide flaws let a prompt injection run code on developers' machines through Cursor
NewsResearchers disclose 'Agentjacking,' an MCP injection attack that hijacks AI coding agents via Sentry