AI and LLM vulnerabilities

5 types in this category.

  • Prompt injection

    How prompt injection works, why an AI cannot fully separate instructions from data, IPA, MIC and OWASP advice, published cases, and how to check your AI.

  • Data leakage through LLMs

    How information leaks through generative AI via staff input, internal documents and instruction text, with OWASP, MIC and IPA sources, cases, and checks.

  • Excessive agency

    How AI agents end up with too many tools and permissions, drawn from OWASP, NIST, NCSC and MCP documents, plus how to check your setup and narrow it.

  • Data poisoning

    How data poisoning of AI training and reference data works, how fake content enters documents and models, public sources, and how to check your own AI.

  • Insecure output handling

    What happens when AI output reaches screens, databases and commands unchecked, with IPA and OWASP guidance, two CVE cases, and how to check your AI features.

All categories

See what an attacker can see, today

The free URL check returns a grade in under a minute. For costs and next steps, book a free consultation.