Source library · 320 curated entries

Where every claim in SecProve comes from.

A dense reading catalog. Every claim is footnoted. Sort by source, filter by pillar, type, or recency. Built for analysts who want to see what we are standing on.

320SOURCES
143ORGS
50DOMAINS
320ADDED · 90 DAYS
Pillar · multi-selectall 4 selected
Domainsselect pillar(s) above
Browsing the full corpus. Pick pillars above to narrow to specific domains.
9 sources · matching filters · sorted by citation density
Sort
CCybersecurity of AI Systems9 sources
01

Security documentation for LangChain agent framework — sandboxing, tool permissions, prompt injection defenses, and deployment hardening.

GuideIntermediateC11 · Agentic AI SecurityNEW · 1mo ago
Test your knowledge · C11
02

Analysis of risks specific to AI agents: tool use, chain-of-thought exploitation, multi-step task failures, delegation risks. Key for understanding why agents create new attack surfaces beyond single-turn interactions.

ResearchIntermediateC11 · Agentic AI SecurityNEW · 22d ago
Test your knowledge · C11
03

Anthropic's open protocol for connecting AI models to external tools and data sources. Critical reading for agentic AI security.

FrameworkIntermediateC11 · Agentic AI SecurityNEW · 1mo ago
Test your knowledge · C11
04

Annual trends report. AI trust, risk, and security management (AI TRiSM) has been featured prominently. Good for strategic-level questions about where the industry is heading.

ResearchIntermediateC11 · Agentic AI SecurityNEW · 22d ago
Test your knowledge · C11
05

Framework for agentic AI governance: scope control, human oversight, auditability, containment. Defines key properties agents should have and failure modes to prevent.

ResearchIntermediateC11 · Agentic AI SecurityNEW · 22d ago
Test your knowledge · C11
06

Extension of the LLM Top 10 specifically for agentic patterns. Covers excessive agency, insecure plugin/tool design, and multi-agent trust boundaries.

Test your knowledge · C11
07

OWASP guidance on securing agentic AI systems — tool use, delegation chains, memory poisoning, and multi-agent architectures.

GuideIntermediateC11 · Agentic AI SecurityNEW · 1mo ago
Test your knowledge · C11
08

Survey of tool-using, retrieval-augmented, and reasoning LMs. The architectural foundation for understanding agent capabilities and their security implications.

ResearchIntermediateC11 · Agentic AI SecurityNEW · 22d ago
Test your knowledge · C11
09

ToolEmu framework for evaluating agent risks in sandboxed environments. 36 risk categories across tool use failures. Practical methodology for agent security testing questions.

ResearchIntermediateC11 · Agentic AI SecurityNEW · 22d ago
Test your knowledge · C11

Ready to test what you've learned?

Our questions are built directly from these resources. Take a quiz and see how your knowledge stacks up.