control

NIST-AGI-06 — Prompt-injection prevention and limits on resulting harm

The paper explicitly asks which controls help prevent direct and indirect prompt injection and which controls can limit its impact after an injection succeeds.

Record JSON · Open in map · Data retrieval guide

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

Attributes

framework
nist-ai-agent-identity
type
preventive
category
technical

Details

control_id
NIST-AGI-06
framework
nist-ai-agent-identity
group
Agent Identity and Authorization Topics
domains
    risk_count
    0
    control_type
    preventive
    control_category
    technical
    automation
    hybrid
    key_control
    False
    requirement_status
    Not provided
    requirement_frequency
    Not provided
    source_url
    https://www.nccoe.nist.gov/sites/default/files/2026-02/accelerating-the-adoption-of-software-and-ai-agent-identity-and-authorization-concept-paper.pdf#page=5
    source_pages
    Concept paper p. 4: Prompt Injection prevention and mitigation
    statement
    The paper explicitly asks which controls help prevent direct and indirect prompt injection and which controls can limit its impact after an injection succeeds.

    Source

    Read the source

    Connections