PREVIEW. This is how it will look in an inbox; it was not sent to you. Each real email carries its own unsubscribe link and Keryn's postal address. KERYN HEADLINES Weekly, week 28 of 2025 Retrospective Covers 1 July 2025 11:00 to 8 July 2025 11:00 UTC Web: https://keryn.dev/headlines/weekly/2025-W28/ TOP DEVELOPMENTS [1] Public exploits released for Citrix Bleed 2 NetScaler flaw, patch now BleepingComputer · Research · https://bleepingcomputer.com/news/security/public-exploits-released-for-citrixbleed-2-netscaler-flaw-patch-now [2] Hiding Prompt Injections in Academic Papers Schneier on Security · Research · https://schneier.com/blog/archives/2025/07/hiding-prompt-injections-in-academic-papers.html [3] Over 40 Malicious Firefox Extensions Target Cryptocurrency Wallets, Stealing User Assets The Hacker News · Research · https://thehackernews.com/2025/07/over-40-malicious-firefox-extensions.html [4] Critical Vulnerability in Anthropic's MCP Exposes Developer Machines to Remote Exploits The Hacker News · Research · https://thehackernews.com/2025/07/critical-vulnerability-in-anthropics.html SAST [5] We Urgently Need Privilege Management in MCP: A Measurement of API Usage in MCP Ecosystems arXiv · Research · https://arxiv.org/abs/2507.06250 [6] Improving LLM Reasoning for Vulnerability Detection via Group Relative Policy Optimization arXiv · Research · https://arxiv.org/abs/2507.03051 [7] Rethinking Broken Object Level Authorization Attacks Under Zero Trust Principle arXiv · Research · https://arxiv.org/abs/2507.02309 [8] CoRe: Benchmarking LLMs Code Reasoning Capabilities through Static Analysis Tasks arXiv · Research · https://arxiv.org/abs/2507.05269 SCA [9] Understand your software’s supply chain with GitHub’s dependency graph GitHub · Analysis · https://github.blog/security/supply-chain-security/understand-your-softwares-supply-chain-with-githubs-dependency-graph [10] Dependabot supports configuration of a minimum package age GitHub · Analysis · https://github.blog/changelog/2025-07-01-dependabot-supports-configuration-of-a-minimum-package-age DAST [11] RVISmith: Fuzzing Compilers for RVV Intrinsics arXiv · Research · https://arxiv.org/abs/2507.03773 [12] On the Surprising Efficacy of LLMs for Penetration-Testing arXiv · Research · https://arxiv.org/abs/2507.00829 AGENTIC SDLC [13] Last Week In AppSec for 08. July 2025 Checkmarx · Analysis · https://checkmarx.com/zero-post/last-week-in-appsec-2025-07-08 [14] 5 ways to transform your workflow using GitHub Copilot and MCP GitHub · Analysis · https://github.blog/ai-and-ml/github-copilot/5-ways-to-transform-your-workflow-using-github-copilot-and-mcp [15] EchoLeak (CVE-2025-32711) Show us That AI Security is Challenging Checkmarx · Analysis · https://checkmarx.com/zero-post/echoleak-cve-2025-32711-show-us-that-ai-security-is-challenging REMEDIATION [16] Grafana releases critical security update for Image Renderer plugin BleepingComputer · Analysis · https://bleepingcomputer.com/news/security/grafana-releases-critical-security-update-for-image-renderer-plugin [17] Critical Cisco Vulnerability in Unified CM Grants Root Access via Static Credentials The Hacker News · Analysis · https://thehackernews.com/2025/07/critical-cisco-vulnerability-in-unified.html TRUST [18] Red Teaming AI Red Teaming arXiv · Research · https://arxiv.org/abs/2507.05538 [19] Strategic Alignment Patterns in National AI Policies arXiv · Research · https://arxiv.org/abs/2507.05400 [20] Manage artifact attestations with deletion, filtering, and bulk actions GitHub · Analysis · https://github.blog/changelog/2025-07-01-manage-artifact-attestations-with-deletion-filtering-and-bulk-actions MODELS [21] Optimus: A Robust Defense Framework for Mitigating Toxicity while Fine-Tuning Conversational AI arXiv · Research · https://arxiv.org/abs/2507.05660 [22] Q-Detection: A Quantum-Classical Hybrid Poisoning Attack Detection Method arXiv · Research · https://arxiv.org/abs/2507.06262 [23] CLIP-Guided Backdoor Defense through Entropy-Based Poisoned Dataset Separation arXiv · Research · https://arxiv.org/abs/2507.05113 [24] Beyond Training-time Poisoning: Component-level and Post-training Backdoors in Deep Reinforcement Learning arXiv · Research · https://arxiv.org/abs/2507.04883 AI SECURITY [25] How Not to Detect Prompt Injections with an LLM arXiv · Research · https://arxiv.org/abs/2507.05630 [26] AI Agent Smart Contract Exploit Generation arXiv · Research · https://arxiv.org/abs/2507.05558 [27] A Systematization of Security Vulnerabilities in Computer Use Agents arXiv · Research · https://arxiv.org/abs/2507.05445 [28] SAMEP: A Secure Protocol for Persistent Context Sharing Across AI Agents arXiv · Research · https://arxiv.org/abs/2507.10562 ADVISORIES IN THIS WINDOW 239 npm advisories · 233 critical · 2 high · 3 moderate · 1 low 13 PyPI advisories · 7 high · 6 moderate 6 Packagist advisories · 4 high · 2 moderate 3 Go advisories · 2 high · 1 moderate 2 crates.io advisories · 2 moderate 2 Maven advisories · 2 moderate 1 RubyGems advisory · 1 moderate All advisories: https://keryn.dev/headlines/advisories/ Titles, links and short excerpts only; every item links to its source. Preview: the unsubscribe link and Keryn's postal address are added to each email when it is sent.