Tool misuse & exploitation
Agents chain legitimate tools unsafely or invoke sensitive APIs
categoryAI/ML and emerging attacksseverityVery Highlabnot yet measured
Classification
20 values: 12 reviewed, 7 imported, 1 derived. What do these mean?
Exploitability
| Attack vector | AI model manipulation |
|---|---|
| Reach (CVSS) | Network |
| Attack complexity | Low |
| Privileges required | None |
| User interaction | None |
| Attacker skill required | Medium |
| Resources required | Low |
| Likelihood / prevalence | Medium |
| Maturity | Proof of concept |
Impact & scope
| Severity | Very High |
|---|---|
| Impact | AvailabilityConfidentialityFinancialIntegrity |
| Platform | AI System |
| Environment | AI system |
| Target asset class | ML model / agent |
| Kill-chain phase (tactic) | ExecutionLateral MovementPrivilege Escalation |
Detection & response
Mitigated by 12
- AML.M0020 atlas-mitigation
- AML.M0021 atlas-mitigation
- AML.M0022 atlas-mitigation
- AML.M0024 atlas-mitigation
- AML.M0026 atlas-mitigation
- AML.M0027 atlas-mitigation
- AML.M0028 atlas-mitigation
- AML.M0029 atlas-mitigation
- AML.M0030 atlas-mitigation
- AML.M0032 atlas-mitigation
- AML.M0033 atlas-mitigation
- AML.M0035 atlas-mitigation
Framework references
- Primary source: https://goteleport.com/blog/owasp-top-10-agentic-applications/
- owasp-asi: ASI02 (primary)
- atlas: AML.T0053
Evidence & sources
- ev-0001 (Cyber Attack Taxonomy) — Name, definition and Example/ID taken verbatim from the 'AI/ML and emerging attacks' table, line 629 of Cyber-Attack-Taxonomy.md