Tag: Unicode
-
Embrace The Red: Sneaking Invisible Instructions by Developers in Windsurf
Source URL: https://embracethered.com/blog/posts/2025/windsurf-sneaking-invisible-instructions-for-prompt-injection/ Source: Embrace The Red Title: Sneaking Invisible Instructions by Developers in Windsurf Feedly Summary: Imagine a malicious instruction hidden in plain sight, invisible to you but not to the AI. This is a vulnerability discovered in Windsurf Cascade, it follows invisible instructions. This means there can be instructions in a file or…
-
Embrace The Red: Amazon Q Developer for VS Code Vulnerable to Invisible Prompt Injection
Source URL: https://embracethered.com/blog/posts/2025/amazon-q-developer-interprets-hidden-instructions/ Source: Embrace The Red Title: Amazon Q Developer for VS Code Vulnerable to Invisible Prompt Injection Feedly Summary: The Amazon Q Developer VS Code Extension (Amazon Q) is a very popular coding agent, with over 1 million downloads. In previous posts we showed how prompt injection vulnerabilities in Amazon Q could lead…
-
Embrace The Red: Amp Code: Invisible Prompt Injection Fixed by Sourcegraph
Source URL: https://embracethered.com/blog/posts/2025/amp-code-fixed-invisible-prompt-injection/ Source: Embrace The Red Title: Amp Code: Invisible Prompt Injection Fixed by Sourcegraph Feedly Summary: In this post we will look at Amp, a coding agent from Sourcegraph. The other day we discussed how invisible instructions impact Google Jules. Turns out that many client applications are vulnerable to these kinds of attacks…
-
Embrace The Red: Google Jules is Vulnerable To Invisible Prompt Injection
Source URL: https://embracethered.com/blog/posts/2025/google-jules-invisible-prompt-injection/ Source: Embrace The Red Title: Google Jules is Vulnerable To Invisible Prompt Injection Feedly Summary: The latest Gemini models quite reliably interpret hidden Unicode Tag characters as instructions. This vulnerability, first reported to Google over a year ago, has not been mitigated at the model or API level, hence now affects all…
-
CSA: Homoglyph Attacks & Domain Squatting
Source URL: https://cloudsecurityalliance.org/articles/homoglyph-attacks-domain-squatting-the-hidden-risk-to-your-brand Source: CSA Title: Homoglyph Attacks & Domain Squatting Feedly Summary: AI Summary and Description: Yes Summary: The text highlights the escalating threat posed by homoglyph-based domain squatting, emphasizing its potential impact on brand trust and cloud security. It underscores the need for proactive DNS posture management to detect and mitigate these risks,…
-
Slashdot: Curl Warns GitHub About ‘Malicious Unicode’ Security Issue
Source URL: https://developers.slashdot.org/story/25/05/17/0420236/curl-warns-github-about-malicious-unicode-security-issue?utm_source=rss1.0mainlinkanon&utm_medium=feed Source: Slashdot Title: Curl Warns GitHub About ‘Malicious Unicode’ Security Issue Feedly Summary: AI Summary and Description: Yes Summary: The text discusses a security issue related to the use of Unicode characters in URLs within the Curl project, highlighting the impact of such changes and the subsequent measures taken to address it.…
-
Slashdot: How AI Coding Assistants Could Be Compromised Via Rules File
Source URL: https://developers.slashdot.org/story/25/03/23/2138230/how-ai-coding-assistants-could-be-compromised-via-rules-file?utm_source=rss1.0mainlinkanon&utm_medium=feed Source: Slashdot Title: How AI Coding Assistants Could Be Compromised Via Rules File Feedly Summary: AI Summary and Description: Yes Summary: The text discusses a significant security vulnerability in AI coding assistants like GitHub Copilot and Cursor, highlighting how malicious rule configuration files can be used to inject backdoors and vulnerabilities in…