Human-agent trust exploitation
Persuasive agent output manipulates users into unsafe approvals
categoryAI/ML and emerging attacksseverityMediumlabnot yet measured
Classification
15 values: 5 imported, 1 derived, 9 machine-classified. What do these mean?
Exploitability
| Attack vector | AI model manipulation |
|---|---|
| Reach (CVSS) | Network |
| Attack complexity | High |
| Privileges required | None |
| User interaction | Active |
| Attacker skill required | Medium |
| Resources required | Low |
| Likelihood / prevalence | Medium |
| Maturity | Proof of concept |
Impact & scope
| Severity | Medium |
|---|---|
| Impact | Integrity |
| Platform | AI System |
| Environment | AI system |
| Target asset class | ML model / agent |
| Kill-chain phase (tactic) | Defense Evasion (legacy) (deprecated) |
Detection & response
No linked mitigations or detections yet.
Framework references
- Primary source: https://goteleport.com/blog/owasp-top-10-agentic-applications/
- owasp-asi: ASI09 (primary)
- atlas: AML.T0067
Evidence & sources
- ev-0001 (Cyber Attack Taxonomy) — Name, definition and Example/ID taken verbatim from the 'AI/ML and emerging attacks' table, line 649 of Cyber-Attack-Taxonomy.md
- ev-0002 (Seeded-record enrichment run 2026-09-30 (crosswalk + facet classification)) — Crosswalk to atlas:AML.T0067 as the nearest framework entries; ids verified to exist in the cached catalogues.