Sources#
Summary#
The Open Worldwide Application Security Project — a long-standing nonprofit security community, historically known for the OWASP Top 10 web-application risks. In the agentic era it is the source of the threat taxonomy that structures Zero Trust for AI Agents, it coined the term Least Agency (extending least privilege to agents), and it maintains the AI-BOM standard for supply-chain transparency.
What OWASP contributes to agentic security#
- Agentic threat taxonomy — the framework's Part II ("Current threats to agentic systems") is organized around OWASP-identified threats: prompt injection, tool and resource hijacking, identity and access privilege abuses, memory and context poisoning, and supply chain risks.
- "Least agency" — OWASP's coinage extending least privilege to agentic applications, restricting what each agent tool can do, how often, and where. See Least Agency.
- AI-BOM — OWASP's AI Bill of Materials, an extension of their CycloneDX ML-BOM, available as a web tool. Tracks model provenance, training-dataset lineage, and fine-tuning parameters; the framework recommends wiring it alongside OpenSSF Scorecard so model and code dependencies carry the same risk signals.
Relation to other standards bodies#
In the Zero Trust lineage, OWASP sits alongside the formal government standards the framework cites — NIST (SP 800-207), the NSA (Zero Trust Implementation Guides), CISA (Zero Trust Maturity Model), and international equivalents (UK NCSC, Australia Home Affairs). OWASP supplies the application/agent-level threat vocabulary; the government bodies supply the architecture-level doctrine.
Connections#
- Zero Trust for AI Agents — the framework built on OWASP's agentic threat taxonomy
- Least Agency — OWASP coinage
- Agent Supply Chain Risk — OWASP maintains the AI-BOM used to manage it
- Agentic Prompt Injection / Memory and Context Poisoning — threats in OWASP's agentic taxonomy
- Anthropic — adopts and extends the OWASP taxonomy in its Zero Trust framework
Sources#
- Zero Trust for AI Agents — OWASP cited as the source of the agentic threat taxonomy, "least agency," and the AI-BOM
Cited by 12
- Agentic Prompt Injection×2
Prompt injection is the insertion of malicious instructions that cause an agent to follow attacker…
- Least Agency×2
Least agency is a term coined by Owasp that extends the classic least-privilege principle to…
- Security Debt of Agent-Generated Code×2
Six categories grounded in OWASP secure-coding guidance (Owasp), the CIS Benchmarks, and GitHub…
- Agent Data Injection (ADI)
Owasp — ADI is a new subcategory under the OWASP LLM01 prompt-injection umbrella
- Agent Supply Chain Risk
Owasp — supply chain in the agentic threat taxonomy; maintains the AI-BOM
- Anthropic
Owasp — Anthropic adopts and extends OWASP's agentic threat taxonomy and "least agency" term in the…
- Capability Gating Is Not Authorization
Owasp — the confused-deputy failure is indirect prompt injection under OWASP LLM01 (and MITRE ATLAS…
- MCP Tool Poisoning
Owasp — TPA sits under the OWASP LLM01 indirect-prompt-injection umbrella; Agentjacking is…
- Entities — People, Orgs, Tools & Projects
Owasp — Open Worldwide Application Security Project; source of the agentic threat taxonomy cited…
- Out-of-Band Prompt-Injection Defense
Owasp — the paper builds on OWASP's LLM01:2025 framing and its note that a guardrail model is…
- Self-Propagating Prompt Injection (AI Worms)
Owasp — the source classes the attack as an XPIA under the OWASP LLM01 prompt-injection umbrella
- Zero Trust for AI Agents
Owasp — source of the agentic threat taxonomy and the "least agency" term
Related articles
- Agent Data Injection (ADI)
A new category of indirect prompt injection: malicious payloads disguised as *trusted data* (metadata like a comment's…
- Zero Trust for AI Agents
Anthropic's security framework for deploying autonomous agents: trust nothing / verify everything / assume breach, appl…
- Agentic Prompt Injection
Direct and indirect injection of malicious instructions into an agent; LLMs cannot reliably distinguish information fro…
- Agent Supply Chain Risk
Runtime-composed agent ecosystems expand the supply-chain attack surface: model poisoning (250 docs backdoor a 13B mode…
- MCP Tool Poisoning
The MCP Tool Poisoning Attack (TPA) class: adversarial or compromised MCP servers plant malicious instructions in tool…
