PPhying中文
Curated security research, vulnerabilities, advisories and tools for practitioners.

The OWASP Top 10 for LLMs 2025: How GenAI Risks Are Evolving

hackerone.com | blog | #ai-security | #prompt-injection | #llm | #owasp | #application-security | #hackerone | #top-10 | #genai
📄 Raw .md⬇️ Download .md🔗 Original ↗

Summary

OWASP's Top 10 for LLM Applications 2025 keeps prompt injection at #1 and adds system prompt leakage, vector/embedding weaknesses, and unbounded consumption; HackerOne analyzes changes and defenses.
Published
Collected

Related coverage

blog · hackerone.com
Measuring The Fix: How We Evaluate Frontier Models on Remediation Quality
HackerOne tested frontier models on security fix quality and found the judge mattered more than the model. See how CTEM remediation earns engineer trust.
blog · blog.sentry.security
PIChef. A tool for Prompt Injection inspired by CyberChef
# PIChef. A tool for Prompt Injection inspired by CyberChef #### Sentry 08 Oct 2026 — 6 min read Share Baba Yaga represents PIChef as a keeper of dangerous recipes, mixing strange prompt-injection...
blog · projectdiscovery.io
Continuous PR Security Review
Post-mortem vulnerabilities often look harmless in the diff—they only surface at runtime. ProjectDiscovery says LLM code review hits just 63% precision, so PRs need validation on a running app.
blog · blog.sentry.security
Semantic vs. Token-Based LLM Injections
Contrasting two LLM injection classes: semantic attacks use natural language to override instructions; token-based attacks exploit tokenizer quirks like reserved delimiters and adversarial suffixes.
blog · blog.sentry.security
LLM API Misconfigurations
How LLM API misconfigurations break trust boundaries: exposed messages[], privileged roles, model choice, or generation parameters enable role injection, parameter tampering, and runaway token usage.
blog · blog.sentry.security
ChatML Role Injection (CRI)
Attackers can inject system roles into ChatML message arrays to override developer instructions, invoke hidden tools, and pad payloads for denial-of-wallet DoS; strict schema validation is key.
Back