Source assessmentSupporting
Securing Agentic AI: An Addendum to the Guidelines and Companion Guide on Securing AI Systems 2025 (Draft for Public Consultation)
Securing Agentic AI SystemsRegulatory/legal
Assessment outcome
total 4/6 (actionability 1 + authority 1 + currency 2)
Total4/6
Actionability1/2
Authority1/2
Currency2/2
Authorship & scope
Attribution (G4 evidence)
No evidence recorded for this source.
Issuer authority (evidence)
No evidence recorded for this source.
Issuers, who it governs, legal force and content are on the full record.
Eligibility gates
G1 · Retrievablepass
Passed in screening.
G2 · AI nexuspass
Passed in screening.
G3 · Governance nexuspass
Passed in screening.
G4 · Attributablepass
Passed in screening.
G5 · In forcepass
Passed in screening.
Scored criteria
Actionability
1/2No rationale recorded.
Organisations must carefully consider both the transformative potential and inherent risks these agentic AI systems present.
Authority
1/2No rationale recorded.
This document is published by the CSA, in collaboration with partners across the AI and Cyber communities
Currency
2/2No rationale recorded.
Classification
Coverage topicSecuring Agentic AI Systems
PerspectiveRegulatory/legal
Lifecycle stageN/A cross-cutting
Layerboth
GranularityNot recorded