Synthèse
Agent-based systems would create massive new attack surfaces. "The amount of prompt injection we're about to see propagate across the Internet is going to be staggering."— OpenAI's November 23' Releases, November 2023 Analysis: Prompt injection is now OWASP's #1 LLM vulnerability for 2025. OpenAI stated in December 2025: "Prompt injection is unlikely to ever be fully 'solved.'" 24 CVEs were assigned for AI tool vulnerabilities in December 2025 alone. VERDICT: Called it—endemic status confirmed.
Agent-based systems would create massive new attack surfaces. "The amount of prompt injection we're about to see propagate across the Internet is going to be staggering. "— OpenAI's November 23' Releases, November 2023 Analysis: Prompt injection is now OWASP's #1 LLM vulnerability for 2025. OpenAI stated in December 2025: "Prompt injection is unlikely to ever be fully 'solved. '" 24 CVEs were assigned for AI tool vulnerabilities in December 2025 alone.
VERDICT: Called it—endemic status confirmed.
Source originale
danielmiessler.com
Prompt Injection Isn't a Vulnerability (Most of the Time)
· 25 nov.
Prompt Injection Isn't a Vulnerability (Most of the Time)
· 25 nov.
Prompt Injection Isn't a Vulnerability (Most of the Time)
· 25 nov.
Prompt Injection Isn't a Vulnerability (Most of the Time)
· 25 nov.
CORTEX