Trojanized AI packages / MCP servers
Compromised accounts publish backdoored AI tooling
categoryAI/ML and emerging attacksseverityVery Highlabnot yet measured
Example: LiteLLM
Classification
19 values: 11 reviewed, 5 imported, 3 derived. What do these mean?
Exploitability
| Attack vector | AI model manipulationMalwareSupply chain |
|---|---|
| Reach (CVSS) | Network |
| Attack complexity | Low |
| Privileges required | High |
| User interaction | Passive |
| Attacker skill required | High |
| Resources required | Medium |
| Likelihood / prevalence | Medium |
| Maturity | Emerging |
Impact & scope
| Severity | Very High |
|---|---|
| Impact | AvailabilityConfidentialityIntegrity |
| Platform | AI System |
| Environment | AI system |
| Target asset class | ML model / agent |
| Kill-chain phase (tactic) | Execution |
Detection & response
Mitigated by 5
- AML.M0011 atlas-mitigation
- AML.M0013 atlas-mitigation
- AML.M0016 atlas-mitigation
- AML.M0018 atlas-mitigation
- AML.M0023 atlas-mitigation
Framework references
- Primary source: https://cloud.google.com/blog/topics/threat-intelligence/from-prompting-to-autonomy-the-evolution-of-adversarial-ai/
- atlas: AML.T0011.001 (primary)
Evidence & sources
- ev-0001 (Cyber Attack Taxonomy) — Name, definition and Example/ID taken verbatim from the 'AI/ML and emerging attacks' table, line 639 of Cyber-Attack-Taxonomy.md