Improper output handling
Unsanitised model output passed to browsers, shells or SQL enables injection
categoryAI/ML and emerging attacksseverityHighlabnot yet measured
Classification
17 values: 3 imported, 2 derived, 12 machine-classified. What do these mean?
Exploitability
| Attack vector | AI model manipulationSoftware vulnerabilities |
|---|---|
| Reach (CVSS) | Network |
| Attack complexity | Low |
| Privileges required | None |
| User interaction | None |
| Attacker skill required | Medium |
| Resources required | Low |
| Likelihood / prevalence | Medium |
| Maturity | Established |
Impact & scope
| Severity | High |
|---|---|
| Impact | AvailabilityConfidentialityIntegrity |
| Environment | AI system |
| Target asset class | ML model / agentWeb app / API |
Detection & response
No linked mitigations or detections yet.
Framework references
- Primary source: https://genai.owasp.org/llm-top-10/
- owasp-llm: LLM05:2025 (primary)
- cwe: CWE-116
Evidence & sources
- ev-0001 (Cyber Attack Taxonomy) — Name, definition and Example/ID taken verbatim from the 'AI/ML and emerging attacks' table, line 632 of Cyber-Attack-Taxonomy.md
- ev-0002 (Seeded-record enrichment run 2026-09-30 (crosswalk + facet classification)) — Crosswalk to cwe:CWE-116 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-116 'Improper Encoding or Escaping of Output', a CWE Class-level weakness (CWE 4.20).
Improper Encoding or Escaping of Output