Direct prompt injection
An attempt by the agent's own user, through the agent's normal input channel, to override its instructions or safety behaviour. Distinct from indirect prompt injection because the instruction arrives through the channel the system's designers expected to carry instructions, from the acknowledged party interacting with the agent, even if that party is acting in bad faith.
Defined in 5 GAGE programs, which carry 5 distinct definitions of it. The wording above is taught in Certified Agentic AI Governance Professional (CAAGP).
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.
An attempt by the agent's own user, through the agent's normal input channel, to override its instructions or safety behaviour. Distinct from indirect prompt injection because the instruction arrives through the channel the system's designers expected to carry instructions, from the acknowledged party interacting with the agent, even if that party is acting in bad faith.
Prompt injection in which the attacker types the overriding instruction straight into the system ("ignore your previous instructions and do X"). The Chevrolet dollar-truck attack is the canonical example.
A form of prompt injection where the attacker types adversarial instructions straight into the AI system's own interface, attempting to override its intended behavior in real time.
An attack in which the adversary types the malicious instructions straight to the AI (for example, a user typing an override into a chatbot, as in the Chevrolet case).
A prompt injection attack where the malicious instruction is typed directly by the user into the AI system's input.
Where it is taught
The exact lessons this term appears in. The first module of every program is free with a free account.
- Prompt Injection and Jailbreak Defense · AI Security Fundamentals, Certified AI Practitioner: Workplace Foundations
- Red Teaming an Agent Starts With Its Use Case, Not a Generic Checklist · Testing and Red-Teaming, Certified Agentic AI Governance Professional (CAAGP)
- The injectable corpus: documents that attack the AI that reads them · Poison, Leaks, and the Adversary, Certified AI Data Governance Professional (CADGP)
- Red-teaming your own system: attacks a motivated user will find · Evaluation and Trust, Certified AI Governance Professional (CAIGP)
- Security and Red-Teaming: Adversarial Attacks, Prompt Injection, Supply Chain · Technical Credibility Deep Dive, The AI Lobbyist: Certified AI Policy Strategist
Where it shows up at work
A definition is where Direct prompt injection 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.
3 lessons on this page teach it as a primary outcome.
Finds unapproved AI use, sets which tools are approved and what may be pasted, and detects leakage without policing every keystroke.
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.
- Cybersecurity Risk Analystneeds working knowledge
- Chief Information Security Officer, AI security focusneeds it at depth
- Chief Technology Officer, AI engineering editionneeds it at depth
- AI Incident Response Leadneeds it at depth · 1 open posting this week
- AI Security Architectneeds it at depth · 8 open postings this week
- AI Governance Engineerneeds it at depth · 7 open postings this week
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; ISO/IEC 27001 Annex A.
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.