# agentic-attacks
7 artikelengetagd met “agentic-attacks”
Analyse van prompt-injectieketens
Het analyseren van ketens van prompt-injectie-aanvallen over AI-systemen met meerdere stappen, inclusief propagatie van indirecte injectie, agentic misbruik en correlatie van aanvallen tussen systemen.
Lab: manipulatie van agentgeheugen
Hands-on lab for injecting persistent instructions into an agent's memory and context that affect future interactions and conversations.
Lab: injection via function calling
Hands-on lab for exploiting function calling mechanisms by crafting inputs that manipulate which functions get called and with what parameters.
Lab: misbruik van MCP-servers
Hands-on lab for attacking a vulnerable MCP server, demonstrating tool shadowing, consent phishing, and server impersonation techniques.
Lab: rechtenescalatie bij agents
Hands-on lab for tricking AI agents into performing actions beyond their intended scope through privilege escalation techniques.
Lab: poisoning van toolresultaten
Hands-on lab for poisoning tool outputs to redirect agent behavior by injecting malicious content through tool results.
Lab: workflow-hijacking
Hands-on lab for redirecting multi-step agent workflows to perform unintended actions by manipulating intermediate states and control flow.