Prompt injection and jailbreak resistance

Attack success rate, including injections hidden in chart text.

Who judgesAutomatable
EvidenceGrade E4
Product typeCross-cuttingID X12

What prompt injection and jailbreak resistance means

Attack success rate, including injections hidden in chart text.

Why it matters. Health tools read text they don't control, like chart notes and uploaded documents. Hidden instructions can hijack them.

Example, illustrative

A scanned referral contains hidden text telling the agent to ignore safety rules.

How to measure it

01

Define the unit

Decide whether you count per sentence, per note, per patient or per call.

02

Sample on purpose

Pick cases that cover specialties, languages and rare events, not only easy ones.

03

Judge with clinicians

Clinicians label a sample. Graders are then checked against those labels.

04

Report the margin

Show an interval, and the grader's own error rate beside the score.

Watch out for

A single average hides rare, serious errors and weaker subgroups.

What a good report shows

A number with a clear unit, a stated sample, a margin and the grader's agreement with clinicians.

Report the unit (per sentence, per note, per patient), the sampling method, the severity scale, and how often the automated grader agreed with clinicians compared with how often clinicians agreed with each other.

Reviewed by the Precision research team.

How strong is the evidence

E4 · Recalled, not verified. Recalled from background knowledge and not verified. Treat it as a lead for investigation, not a finding.

What the sources say

No healthcare-specific benchmark verified; chart-text injection is E4.

  • Automatable. Can be scored by software, including an AI grader that is spot-checked against clinicians.

Found something out of date? Write to hello@precision.example.

Quick answers

What is prompt injection and jailbreak resistance in healthcare AI?

Attack success rate, including injections hidden in chart text. It sits in the every product type group.

Why does prompt injection and jailbreak resistance matter?

Health tools read text they don't control, like chart notes and uploaded documents. Hidden instructions can hijack them. A scanned referral contains hidden text telling the agent to ignore safety rules.

How is prompt injection and jailbreak resistance measured?

Define the unit, then Sample on purpose, then Judge with clinicians, then Report the margin. Report the unit (per sentence, per note, per patient), the sampling method, the severity scale, and how often the automated grader agreed with clinicians compared with how often clinicians agreed with each other.

What should I watch out for with prompt injection and jailbreak resistance?

A single average hides rare, serious errors and weaker subgroups. A good report gives: a number with a clear unit, a stated sample, a margin and the grader's agreement with clinicians.

Can prompt injection and jailbreak resistance be automated?

Largely yes, including AI graders that are spot-checked against clinicians. Report the grader's error rate beside every score.

Measure prompt injection and jailbreak resistance on your own data