Mindgard

Mentions · 7d0
Mentions · 30d0
All mentions1
First seenAug 28, 2026
Last mentionedAug 28, 2026

Timeline

1 articles · newest first

Amazon Kiro Prompt Injection Can Exfiltrate Sensitive Data Through Kiro Powers

Mindgard found a prompt injection flaw in Amazon Kiro IDE letting attacker-controlled workspace files exfiltrate sensitive local data; fixed in version 0.8.140.

The Hacker NewsAug 28, 18:35 UTC · Aug 28, 2026AI safety & securityCVE-2026-10591 CVE-2026-35603 CVE-2026-257251

Related CVEs

by mentions

CVE-2026-10591<1%8.6
Insufficient access control restrictions in the file write tool in Amazon Kiro IDE before version 0.11 might allow remote unauthenticated actors to execute…
published Jun 2, 2026amazon kiro ide
CVE-2026-25725<1%7.7
Claude Code: Claude Code's bubblewrap sandboxing mechanism failed to properly protect the .claude/settings.json configuration file when it did…
published Feb 6, 2026anthropic claude code
CVE-2026-35603<1%5.4
Claude Code: Claude Code loaded the system-wide default configuration from C:\ProgramData\ClaudeCode\managed-settings.json without validating…
published Apr 17, 2026anthropic claude code

Appears with

Amazonorganization · 1
GitHub Copilot CLIproduct · 1
Intezerorganization · 1
The Hacker Newsorganization · 1
Anthropicvendor · 1
Kiro Powersproduct · 1
Gemini CLIproduct · 1
Mindgardvendor · 1
Claude Codeproduct · 1
Kiro IDEproduct · 1
Googlevendor · 1
OpenAIvendor · 1
Cursorproduct · 1
OpenAI Codex CLIproduct · 1
Amazonvendor · 1
GitHubvendor · 1

Entities are extracted by the model from each article. First seen Aug 28, 2026, last mentioned Aug 28, 2026. Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.