This site uses cookies for analytics via Microsoft Clarity. We only enable it after your consent. See our Privacy Policy.
Sujith Quintelier
  • Resume
  • Archives
  • Taxonomy
    • Tags
    • Categories
    • Series
  • Tools
    • CIDR Calculator
    • Certification Renewal Tracker
    • Tech Radar
    • UBB Simulator
  • Updates
  • Legal
    • Contact
    • About
    • Privacy
    • Cookies
  • linkedin
  • github
  • twitter
  • mastodon
  • bsky
  • facebook
  • instagram
  • buymeacoffee

  • Toggle theme

Back to updates

Prompt-Injection - 1

2026 (2)

September (1)

security: ASCII smuggling crosses over from AI prompt injection to phishing evasion

Microsoft Security Blog

2026-09-03

Microsoft reports that invisible Unicode characters, previously used in AI prompt injection, are now being used to hide words from email filters as part of phishing evasion. The technique relies on obfuscating text before parsers process it.

July (1)

github: CodeQL 2.26.0 adds Kotlin 2.4.0 support and AI prompt injection detection

GitHub

2026-07-10

CodeQL 2.26.0 adds support for Kotlin 2.4.0 and introduces detection for AI prompt injection issues in code scanning. The release updates the static analysis engine used by GitHub code scanning.

© Copyright 2018-Present Sujith Quintelier All Rights Reserved • RSS

Privacy • Cookies • Contact

Based on Bootstrap. Icons from Bootstrap Icons and Font Awesome. Web fonts from Google.

Source Code