← All tags · All resources · All guides

#owasp

3 resources and 1 guide tagged #owasp on ChangeGamer.

• Agentic Security Checklist · Guide
  Cross-vendor, threat-surface-organized security checklist for building and operating AI agents — synthesizing OWASP, NIST, Anthropic, OpenAI, Google SAIF, and MITRE ATLAS.
• AI Red Teaming Tools for LLM Apps and Agents: garak, PyRIT, promptfoo · Guide
  Decision rule for choosing an open-source AI red-teaming tool — garak (probe/detector scanner), PyRIT (Microsoft, attack orchestration), promptfoo (config-driven, CI-friendly) — plus the OWASP GenAI Red Teaming Guide and what automated scanning does not prove.
• MCP Tool Poisoning: Definition, Attack Variants, and Defenses · Guide
  MCP tool poisoning is an attack where the tool metadata an agent reads (descriptions, schemas) carries hostile instructions or altered contracts. Definition, OWASP MCP03 mapping, what the MCP spec requires of clients, and a pin-scan-confirm defense checklist.

Guides

• How to Manage Secrets for AI Agents in Production · guide
  Why single-agent credential issuance is not the whole secrets problem: auditing which tool servers and MCP connectors hold credentials on an agent's behalf, treating provider-side prompt caches as a disclosure surface, and the named frameworks — OWASP's Secrets Management Cheat Sheet, Twelve-Factor config, and the OWASP GenAI project — that govern the rest.