error · Section 7: Safety instructions

Rule 7.1: Use an applicable word to identify the level of risk

Immediately identify the level of risk in a safety instruction with an applicable signal word (or symbol) — use "warning" when there is a risk of injury or death, and "caution" when there is only a risk of damage to objects, tools, or equipment. If both a warning-level and a caution-level risk are present together, label the instruction as a "warning."

Safety instructions are where a model's findings are least reliable and a wrong rewrite costs most. Nothing a prompt returns on a warning or caution should reach a reader without a person who knows the standard having read it first.

What a checker looks for

A clear deviation from the rule.

  • Flag any safety-relevant instruction (text describing a hazardous action, hazardous material, or a precaution against harm) that has no leading signal word or symbol identifying its risk level.
  • Flag a "CAUTION" label on an instruction whose described hazard is actually a risk of injury or death — it must be labeled "WARNING" instead.
  • When an instruction describes both a risk of injury/death and a risk of property damage together, flag anything other than a "WARNING" label as incorrect.

What this rule does not cover

  • STE does not mandate a specific format (uppercase text, colon placement, boldface, icon style) for the signal word — only that an applicable word or symbol identifying the risk level is present. Do not flag pure formatting/style-guide choices under this rule.
  • Alternative words such as "danger," "attention," or "notice," or graphical safety symbols, are not blanket-approved substitutes for "warning"/"caution" by ASD-STE100 itself — the standard says other industries or domains can use different words or categories. Treat use of an alternative signal word as domain/style-directive-dependent: confirm it against the applicable technical-publication specification, style guide, or official directive (e.g. ANSI Z535, ISO 3864, ISO 45001), and confirm it communicates the correct risk level, before treating it as compliant.

How to fix it

Determine the true severity of the hazard from its described consequences (injury/death vs. property damage only) and prefix the instruction with the matching signal word — "WARNING" for injury/death or combined risks, "CAUTION" for damage-only risks — rewriting any vague hazard language into a concrete statement of what can happen.

Constraints on the fix

  • Do not downgrade a warning to a caution to soften the tone — the signal word must match the actual severity of the risk described, not the writer's preference.

Examples

Not STE: CAUTION: EXTREME CLEANLINESS OF OXYGEN TUBES IS IMPERATIVE.

STE: WARNING: MAKE SURE THAT THE OXYGEN TUBES ARE FULLY CLEAN. OXYGEN AND GREASE MAKE AN EXPLOSIVE MIXTURE. AN EXPLOSION CAN CAUSE INJURY OR DEATH.

The non-STE version labels the instruction "CAUTION" and states only an abstract requirement; since dirty oxygen tubes create an explosion risk with potential injury or death, the standard requires a "WARNING" label and a concrete statement of the hazard.

Not STE: Keep your hands away from the blade area during operation.

STE: WARNING: ALWAYS KEEP YOUR HANDS AND FEET AWAY FROM THE BLADE. WHEN THE MOTOR OPERATES, THE BLADE TURNS AND CAN CAUSE INJURY.

The non-STE version has no signal word at all identifying the level of risk; the STE version leads with "WARNING" because the hazard is personal injury.

Related rules

Where this fits in AI governance

A rule a checker can test is a rule a model can be held to. The same discipline, on the governance side of this site.

Source

ASD-STE100 Issue 9, Section 7 - Safety instructions, page 1-7-2.

This page is commentary and does not reproduce the standard. About this rule pack.