Rogue agents
Compromised or misaligned agents deviate while appearing legitimate
categoryAI/ML and emerging attacksseverityHighlabnot yet measured
Classification
15 values: 1 derived, 14 machine-classified. What do these mean?
Exploitability
| Attack vector | AI model manipulation |
|---|---|
| Reach (CVSS) | Network |
| Attack complexity | High |
| Privileges required | None |
| User interaction | None |
| Attacker skill required | Medium |
| Resources required | Low |
| Likelihood / prevalence | Low |
| Maturity | Theoretical |
Impact & scope
| Severity | High |
|---|---|
| Impact | AvailabilityConfidentialityIntegrity |
| Environment | AI system |
| Target asset class | ML model / agent |
Detection & response
No linked mitigations or detections yet.
Framework references
- Primary source: https://goteleport.com/blog/owasp-top-10-agentic-applications/
- owasp-asi: ASI10 (primary)
Evidence & sources
- ev-0001 (Cyber Attack Taxonomy) — Name, definition and Example/ID taken verbatim from the 'AI/ML and emerging attacks' table, line 650 of Cyber-Attack-Taxonomy.md