Slopsquatting
Package names LLMs hallucinate pre-registered so generated code installs malware
categoryAI/ML and emerging attacksseverityHighlabnot yet measured
Classification
18 values: 11 reviewed, 5 imported, 2 derived. What do these mean?
Exploitability
| Attack vector | AI model manipulationSupply chain |
|---|---|
| Reach (CVSS) | Network |
| Attack complexity | Low |
| Privileges required | None |
| User interaction | Active |
| Attacker skill required | Medium |
| Resources required | Low |
| Likelihood / prevalence | Medium |
| Maturity | Proof of concept |
Impact & scope
| Severity | High |
|---|---|
| Impact | AvailabilityConfidentialityIntegrity |
| Platform | AI System |
| Environment | AI system |
| Target asset class | ML model / agent |
| Kill-chain phase (tactic) | Resource Development |
Detection & response
No linked mitigations or detections yet.
Framework references
- Primary source: https://www.trendaisecurity.com/en-us/resources-insights/deep-research/slopsquatting-when-ai-agents-hallucinate-malicious-packages
- atlas: AML.T0060 (primary)
Evidence & sources
- ev-0001 (Cyber Attack Taxonomy) — Name, definition and Example/ID taken verbatim from the 'AI/ML and emerging attacks' table, line 645 of Cyber-Attack-Taxonomy.md