Back to Academy
Relevance 8/10Safety and PolicyAdvanced8 min read
Prompt Injection Detection
Prompt injection detection identifies attempts to override system behavior or safety constraints.
Why it matters for annotators
Prompt-injection defense is now a key safety evaluation area.
Visual mental model
Prompt/context -> detect override intent -> safe handling class.
Examples (bad vs good)
Scenario: Real annotation scenario involving Prompt Injection Detection
Bad: Labeling quickly without applying project rubric.
Good: Applying rubric criteria, documenting rationale, and escalating uncertainty.
Common mistakes
- Skipping guideline details for edge cases.
- Applying inconsistent criteria across similar samples.
- Avoiding escalation even when uncertain.
Submission checklist
- Read the latest guideline update before each batch.
- Apply rubric dimensions explicitly in each decision.
- Escalate ambiguous items with concise rationale.