Direct prompt injection
User input overrides the system prompt to change behaviour
categoryAI/ML and emerging attacksseverityHighlabnot yet measured
Classification
17 values: 10 reviewed, 5 imported, 2 derived. What do these mean?
Exploitability
| Attack vector | AI model manipulationSoftware vulnerabilities |
|---|---|
| Reach (CVSS) | Network |
| Attack complexity | Low |
| Privileges required | None |
| User interaction | None |
| Attacker skill required | Low |
| Resources required | Low |
| Likelihood / prevalence | High |
| Maturity | Emerging |
Impact & scope
| Severity | High |
|---|---|
| Impact | ConfidentialityIntegrity |
| Platform | AI System |
| Environment | AI system |
| Target asset class | ML model / agent |
| Kill-chain phase (tactic) | Execution |
Detection & response
Mitigated by 3
Framework references
- Primary source: https://genai.owasp.org/llm-top-10/
- owasp-llm: LLM01:2025 (primary)
- atlas: AML.T0051.000
Evidence & sources
- ev-0001 (Cyber Attack Taxonomy) — Name, definition and Example/ID taken verbatim from the 'AI/ML and emerging attacks' table, line 605 of Cyber-Attack-Taxonomy.md