Daily, Friday 26 June 2026
Reconstructed on 19 November 2026 from archived source metadata.
From the editor
The editor's note for this issue is not available. The developments below were selected and ranked automatically from the sources listed.
Top developments
- 1
Interesting Paper Exploring Prompt Injection
This is a fascinating explotation of how LLMs fall for prompt injection attacks. It turns out that they learn to recognize the style of text in different role/instruction blocks, and not just the tags. Their conclusion: Role tags were a formatting trick that became the security…
- 2
CVE-2026-12569: PTC Windchill and FlexPLM Improper Input Validation Vulnerability added to CISA's Known Exploited Vulnerabilities catalog
PTC Windchill and FlexPLM contains an improper input validation vulnerability allowing an unauthenticated, remote attacker to execute arbitrary code by sending a malicious request to the network. Known to be used in ransomware campaigns. US federal agencies must act by 2026-06-28
- 3
New macOS malware embeds fake errors to confuse AI analysis tools
A newly discovered macOS malware dubbed "Gaslight" is designed to confuse AI-assisted malware analysis tools by hiding prompt injection strings and fake debugging data within the executable.
Further reading, by topic
Advisories in this window
- 44 npm advisories42 critical · 1 moderate · 1 low
- 19 NuGet advisories5 high · 14 moderate
- 10 PyPI advisories1 critical · 2 high · 7 moderate
- 6 Maven advisories4 high · 1 moderate · 1 low
- 6 Go advisories3 high · 3 moderate
- 2 Packagist advisories2 high
- 2 crates.io advisories1 moderate · 1 low
This edition
49 developments and 89 advisories in the window. Selection and order are automatic: how stories are placed and ranked.