Prompt & Document Injection
Malicious instructions in untrusted content that manipulate AI behaviour.
Expert-led penetration testing for LLM applications, AI agents and connected infrastructure. Uncover exploitable risks in tool permissions, data access and autonomous actions.



“Security and trust are essential when building a platform that helps organisations manage procurement and compliance. Capture The Bug has made penetration testing a more collaborative and transparent process for our team. Having direct access to their pentesters, clear visibility of findings and a straightforward approach to remediation helps us address risks efficiently while continuing to develop and improve our platform.”
Independent Assurance
CREST-Accredited Penetration Testing- AI Security Risks
Four critical security risks across AI applications and connected systems.
Malicious instructions in untrusted content that manipulate AI behaviour.
AI agents performing unauthorised actions through connected business tools.
Sensitive information exposed through AI-connected knowledge and retrieval systems.
Unprotected model endpoints, APIs and services exposing critical systems.
- What We Test
LLM applications, AI agents and connected tools.
Explore AI Penetration TestingModel endpoints, inference APIs and tool integrations.
Explore API Penetration TestingAI-powered applications, dashboards and admin interfaces.
Explore Web Application TestingCloud infrastructure, model storage and AI workloads.
Explore Cloud Penetration TestingMobile apps with integrated AI and connected APIs.
Explore Mobile Penetration TestingExposed AI services, internal networks and access controls.
Explore Network Penetration Testing- How We Work
Expert-led AI penetration testing with live findings, direct specialist collaboration and remediation tracking through one platform.
Agree AI components, connected tools, data access and testing boundaries.
Agreed ScopeSpecialists assess prompt injection, agent permissions and exploitable AI attack paths.
Live FindingsAccess validated findings with technical evidence, severity ratings and remediation guidance.
Validated FindingsWork directly with specialists to address AI security weaknesses.
Fix GuidanceVerify remediation and document outcomes within agreed engagement terms.
Verified FixesDiscuss your AI architecture and security requirements with our specialists.
- Assurance & Evidence
OWASP Top 10 for LLMs
Testing guided by recognised AI security risks.
ISO/IEC 42001
Technical evidence supporting AI governance and risk management.
NIST AI RMF
Security findings supporting AI risk assessment and management.
CREST Security Testing of AI
CREST accreditation for security testing of AI systems.
Validated findings, technical evidence and verified fixes support customer assurance, risk management and relevant compliance requirements.
AI penetration testing extends conventional application security testing to assess risks introduced by LLMs, AI agents and connected systems, including prompt injection, unauthorised tool execution and sensitive data exposure.
Yes. We assess how AI agents interact with APIs, databases and business tools, testing permissions, authorisation boundaries and whether untrusted instructions can trigger unintended actions.
Yes. We assess RAG pipelines and connected knowledge sources for sensitive data exposure, manipulated documents, retrieval permissions and prompt injection through untrusted content.
Yes. Our testing is informed by the OWASP Top 10 for LLM Applications and relevant MITRE ATLAS techniques, tailored to your architecture and agreed scope.
Once your team has addressed a finding, our specialists retest the affected AI workflows, permissions or security controls and document the outcome through the CTB platform, within agreed engagement terms.
Expert-led penetration testing for AI applications and agents.