control

NIST-TEVV-05 — Test direct and indirect prompt injection

Appendix B includes integrity tests for direct and indirect prompt injection, poisoning, obfuscated inputs, and retrieval weaknesses that could alter intended outputs or outcomes.

Record JSON · Open in map · Data retrieval guide

Catalog revision: 24028ffcfc2b295fa1b08ee6caa84b765f0731b321496bf4f548c49ad2177028. A connection does not establish full coverage.

Attributes

framework
nist-ai-tevv-athlon
type
detective
category
technical

Details

control_id
NIST-TEVV-05
framework
nist-ai-tevv-athlon
group
AI Evaluation and Agent Security Testing
domains
    risk_count
    0
    control_type
    detective
    control_category
    technical
    automation
    hybrid
    key_control
    False
    requirement_status
    Not provided
    requirement_frequency
    Not provided
    source_url
    https://nvlpubs.nist.gov/nistpubs/ai/NIST.AI.200-2.ipd.pdf#page=32
    source_pages
    NIST AI 200-2 ipd Appendix B, Table 4, p. 24: Integrity attacks
    statement
    Appendix B includes integrity tests for direct and indirect prompt injection, poisoning, obfuscated inputs, and retrieval weaknesses that could alter intended outputs or outcomes.

    Source

    Read the source

    Connections