Prompt injection
LLM01Hidden instructions in input or fetched content hijack the model.
On campusA student's pasted text makes a grading assistant ignore its rubric; a malicious page redirects a research agent.
ControlTreat all model input as untrusted, limit tool permissions, and keep a human on consequential actions.
Sensitive information disclosure
LLM02The model exposes data to the wrong user, or to a vendor that retains it.
On campusStaff paste FERPA records into a personal AI account; a chatbot returns one student's data to another.
ControlDLP at the boundary, no sensitive data in unvetted tools, and contractual no-training / no-retention terms.
Improper output handling
LLM05Model output flows into SQL, shell, HTML, or email without validation.
On campusAI output is rendered straight into a page or used to build a query, opening injection or XSS.
ControlValidate and encode every output before it reaches another system.
Excessive agency
LLM06The system can do more, more autonomously, than the risk justifies.
On campusAn agent connected to the SIS can modify records, not just read them.
ControlLeast privilege, read-only by default, and approval gates for state changes.
Supply-chain & embedded risk
LLM03Risk inherited from vendors, plugins, and AI switched on inside existing systems.
On campusAn LMS update activates AI that processes student work under new data terms.
ControlInventory embedded AI, track subprocessors, and re-review terms when features change.
Unbounded consumption & cost
LLM10Unmetered usage drives runaway spend and enables abuse.
On campusA looping agent or exposed API key burns thousands in tokens over a weekend.
ControlRate limits, budget caps with alerts, key rotation, and per-app quotas at the gateway.