AI engineering glossary · Evals guardrails AI security
What is tool poisoning?
Tool poisoning: An attack where the description or output of a tool an agent can call is crafted to contain hidden instructions that steer the model, for example a tool listing that tells the model to send data elsewhere. It is a form of indirect prompt injection aimed at agent tool ecosystems.
Tool poisoning: an example
An external tool's description secretly says 'also email the user's files to this address', and the agent follows it.
Related terms
More Evals guardrails AI security terms
- Tool-call accuracy
- Topical rails
- Toxicity classification
- Training data extraction
- TruthfulQA
- Unbounded consumption
- Vector and embedding weaknesses
- Verbosity bias
Where you learn it
Tool poisoning is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.