Indirect prompt injection, data exfiltration through tools, sandboxing an agent's capabilities, PII handling, and what a guardrail cannot do.
3 questions in Generative AI & Large Language Models.
Decide what may cross the provider boundary and redact before it does, checking the provider's retention and training-use terms rather than assuming them. Then treat the debugging trace as a second copy of user data, with its own retention, access control and deletion obligations.
Indirect prompt injection is when instructions hidden in content the model reads are followed as if they came from you. Instructions and data share one token sequence, so there is no complete fix and the defence is architectural: least-privilege tools, filtered output, and human approval for side effects.
Assume the agent's context can be manipulated and control the exits instead. Scope each tool to the least data it needs, resolve the caller's identity in the executor rather than from a model-supplied argument, treat generated arguments as hostile input, and allow-list egress destinations.