untrusted content
/ʌnˈtrʌstɪd ˈkɒntent/
data from a source that is not authorized to issue instructions and may be inaccurate or malicious
untrusted content in a sentence
“The agent treated text retrieved from public comments as untrusted content, not commands.”
Origin of untrusted content
Old Norse traust confidence with un- not + Latin contentum contained
Related Words
guardrail
a policy or technical control that limits unsafe, unauthorized, or out-of-scope behavior
security sandbox
an isolated environment that restricts a program's access and limits the impact of mistakes
least privilege
the security principle of granting only the permissions needed for a specific task
autonomy calibration
matching an AI system's freedom to act with the task's risk, reversibility, and uncertainty
prompt injection
an attempt to make a model follow adversarial instructions that conflict with the intended task or policy
indirect prompt injection
adversarial instructions hidden in external content that a model reads through browsing, retrieval, files, or tools