Blast Radius
What a successor, or an attacker, could reach by pivoting from a single compromised access path into other systems it was never meant to touch; documenting access one system at a time misses it, so the briefing notes, for each high-criticality system, which other systems its access paths can reach.
Defined in 6 GAGE programs, which carry 37 distinct definitions of it. The wording above is taught in Certified AI Governance Professional (CAIGP).
How each discipline defines it
The same term does different work depending on who is using it. These are the definitions as each program teaches them, unedited.
In this topic's discovery method, a qualitative judgment of how much harm would result if a given system, store, or dataset were compromised, deleted, or found to be wrong, used to set a concern flag independent of how visible or well documented the finding already is. A full quantitative blast-radius analysis, tracing exactly which downstream systems a change would break, is Topic 2.3's owned scope.
What a successor, or an attacker, could reach by pivoting from a single compromised access path into other systems it was never meant to touch; documenting access one system at a time misses it, so the briefing notes, for each high-criticality system, which other systems its access paths can reach.
The scope of harm a single failure could cause given the current phase's restrictions. A well-designed phase one is engineered so that its worst plausible failure has a small blast radius, contained by structural restrictions on the three levers, not merely by hope or by monitoring alone.
The total set of data and actions a manipulated AI could reach; the thing least privilege exists to shrink. The everyday user's key prevention question is "if this AI were following an attacker's instructions, what could it reach?"
The scope of impact when a failure occurs. Containing blast radius (via canary releases, feature flags, and workload isolation) keeps a small failure small; the 2024 CrowdStrike outage is the classic example of an uncontained one.
Where it is taught
The exact lessons this term appears in. The first module of every program is free with a free account.
- Risk Assessment in AI Decisions · Critical Thinking and Context Engineering, Certified AI Practitioner: Workplace Foundations
- Basic AI Experimentation with No-Code Tools · Advanced AI Literacy, Certified AI Practitioner: Workplace Foundations
- When to Delegate to AI Agents vs. Handle Tasks Yourself · Agentic AI and Workforce Integration, Certified AI Practitioner: Workplace Foundations
- Prompt Injection and Jailbreak Defense · AI Security Fundamentals, Certified AI Practitioner: Workplace Foundations
- Securing Agent Permissions and Access Boundaries · AI Security Fundamentals, Certified AI Practitioner: Workplace Foundations
- Agent Governance at Enterprise Scale · Bonus: AI Leadership Accelerator, Certified AI Practitioner: Workplace Foundations
- Systemic Risk · The Agent, Deconstructed, Certified Agentic AI Governance Professional (CAAGP)
- The New Risk Factors · Capability and Autonomy, Certified Agentic AI Governance Professional (CAAGP)
- Containing Third-Party Agents · Bounding by Design, Certified Agentic AI Governance Professional (CAAGP)
- Ship the Agent in Stages, Never All at Once · Rollout, Monitoring, and Incident Response, Certified Agentic AI Governance Professional (CAAGP)
Where it shows up at work
A definition is where Blast Radius starts. The lessons above teach it inside the competencies below, which are what job descriptions ask for and what the GAGE credential records. Every link here is drawn from the same careers map that builds a role's readiness check.
Understands prompt injection, data poisoning, model theft, insecure integrations and excessive agent privileges, and the controls that reduce each.
2 lessons on this page teach it as a primary outcome.
Governs AI agents that take actions: tool access, least privilege, interruptibility, cascading actions and accountability for what an agent did.
2 lessons on this page teach it as a primary outcome.
Knows when to trust, verify, escalate or override an AI recommendation, and stays accountable for the decision.
2 lessons on this page teach it as a primary outcome.
Roles that hire for it
Each role page shows the full competency set, what the seat decides, and a readiness check against your own evidence.
- Chief Information Security Officer, AI security focusneeds it at depth
- AI Security Architectneeds it at depth · 8 open postings this week
- Chief Technology Officer, AI engineering editionneeds it at depth
- AI Governance Engineerneeds it at depth · 7 open postings this week
- AI Incident Response Leadneeds it at depth · 1 open posting this week
- Cybersecurity Risk Analystneeds working knowledge
How job descriptions say it
Postings rarely use the textbook word. These are the phrases the careers map reads as asking for the competencies above.
Where the frameworks place it: OWASP Top 10 for LLM Applications; Google SAIF; NIST AI RMF MEASURE 2; IMDA Model AI Governance Framework for Agentic AI.
One interview question about it
What are the security failure modes specific to AI systems, and which conventional control covers none of them?
Asked of candidates for ai security fundamentals. Answering it in your own words is exactly how a GAGE topic is passed, and the credential records the pass where an employer can check it.
If you come from another field
Some backgrounds already carry this competency, and the readiness check gives credit for it.
- Cybersecurity and IT carries it as a claim to back up: Threat modeling and control design transfer; the AI-specific threats are new.
- A computer science or software engineering degree carries it as a claim to back up: Security fundamentals are a course you took, not yet a control you ran.
- A cybersecurity or information assurance degree carries it as work you can show: Security fundamentals are your coursework and your labs.
Terms it appears with
Not an alphabetical neighbourhood: these are the terms taught in the same lessons, ranked by how often they appear together.