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
Connections
- UC-AI-18 — Defend AI interfaces against adversarial input, injection, and endpoint abuse informed_by NIST-AGI-06 — Prompt-injection prevention and limits on resulting harm
- framework
- nist-ai-agent-identity
- control_id
- NIST-AGI-06
- coverage
- guidance
- relationship
- informs
- delta
- Not provided
- source_version
- February 2026 draft concept paper
- provenance
- mapper
- coworkcanvas-compliance-graph
- reviewDate
- 2026-09-07
- direction
- canonical_to_source
- defaultConfidence
- medium
- defaultStatus
- active
- note
- Each member is a documented relationship claim from the canonical unified control to a source control or guidance proposition. relationship: equal|superset_of (full) / intersects_with|subset_of (partial) / informs (guidance). confidence 'medium' = single-mapper, documented, not yet externally corroborated. source_version is the member framework's edition from the standard version register.
- sourcePages
- Concept paper p. 4: Prompt Injection prevention and mitigation
- NIST-AGI-06 — Prompt-injection prevention and limits on resulting harm belongs_to NIST Agent Identity (draft, Feb 2026)
- UC-AI-19 — Constrain agent actions and tool use to authorized scope informed_by NIST-AGI-06 — Prompt-injection prevention and limits on resulting harm
- framework
- nist-ai-agent-identity
- control_id
- NIST-AGI-06
- coverage
- guidance
- relationship
- informs
- delta
- Not provided
- source_version
- February 2026 draft concept paper
- provenance
- mapper
- coworkcanvas-compliance-graph
- reviewDate
- 2026-09-07
- direction
- canonical_to_source
- defaultConfidence
- medium
- defaultStatus
- active
- note
- Each member is a documented relationship claim from the canonical unified control to a source control or guidance proposition. relationship: equal|superset_of (full) / intersects_with|subset_of (partial) / informs (guidance). confidence 'medium' = single-mapper, documented, not yet externally corroborated. source_version is the member framework's edition from the standard version register.
- sourcePages
- Concept paper p. 4: Prompt Injection prevention and mitigation