Insecure inter-agent communication
Unauthenticated agent messaging enables interception and manipulation
categoryAI/ML and emerging attacksseverityMediumlabnot yet measured
Classification
15 values: 2 derived, 13 machine-classified. What do these mean?
Exploitability
| Attack vector | AI model manipulationSoftware vulnerabilities |
|---|---|
| Reach (CVSS) | Adjacent |
| Attack complexity | High |
| Privileges required | None |
| User interaction | None |
| Attacker skill required | Medium |
| Resources required | Low |
| Likelihood / prevalence | Low |
| Maturity | Proof of concept |
Impact & scope
| Severity | Medium |
|---|---|
| Impact | ConfidentialityIntegrity |
| 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: ASI07 (primary)
- cwe: CWE-306
Evidence & sources
- ev-0001 (Cyber Attack Taxonomy) — Name, definition and Example/ID taken verbatim from the 'AI/ML and emerging attacks' table, line 647 of Cyber-Attack-Taxonomy.md
- ev-0002 (Seeded-record enrichment run 2026-09-30 (crosswalk + facet classification)) — Crosswalk to cwe:CWE-306 as the nearest framework entries; ids verified to exist in the cached catalogues.
- ev-0003 (MITRE Common Weakness Enumeration (CWE) 4.20) — Linked to CWE-306 'Missing Authentication for Critical Function', a CWE Base-level weakness (CWE 4.20).
Missing Authentication for Critical Function