TL;DR: Prompt injection hidden in a filing can steer AI review, according to JetStream Security, after a Brazilian labor court fined two lawyers. Document intake now needs screening, provenance checks, and a clean split between instructions and content.
Editorial analysis by NHI Mgmt Group, based on content published by JetStream Security: “Brazilian Court Sanctions Lawyers for Prompt Injection in Court Filing”.
By the numbers:
- The court fined the two law firms 10% of the claim’s value.
Key questions
Q: Why do AI review systems need governance controls for uploaded documents?
A: Because the risk is not only prompt text typed into a chat box.
Q: What are the signs that a document may contain prompt injection?
A: Warning signs include hidden text, strange colour contrasts, unexpected font layering, unusual OCR output, and instructions that speak to the AI rather than the document’s subject.
Q: What breaks when prompt injection is hidden inside a document instead of a chat prompt?
A: The control boundary breaks because the system treats untrusted document text as if it were legitimate input.
Practitioner guidance
- Define hostile-document screening Scan inbound filings and uploads for hidden text, colour-based concealment, OCR anomalies, and other formatting tricks before AI review processes them.
- Separate task instructions from source content Ensure the system prompt, workflow instructions, and document text are isolated so untrusted documents cannot override review behaviour.
- Add human approval for suspicious submissions Route documents with unusual formatting, embedded commands, or provenance gaps to a manual review queue before any automated summarisation or decision support.
Bottom line: The case shows that prompt injection can be embedded inside ordinary documents and still affect an AI review workflow.
Glossary terms: Prompt Injection (Agentic), Document Ingestion Pipeline, Machine-Readable Content Integrity, AI Governance Debt
Explore further
View Full Forum → | NHI Foundation Course → | Our Services → | Read the full analysis →
Prompt injection now belongs in governance, not just model security. This case shows that adversarial instructions can be carried inside ordinary business artefacts and still reach an AI system with decision support value. The governance question is therefore who validates the input boundary, who owns document integrity, and who can block suspicious content before it reaches the model. Practitioners should treat untrusted documents as a first-class control surface.
A question worth separating out:
Q: How should organisations respond when an AI-assisted filing workflow is manipulated?
A: Pause automated handling of the affected workflow, preserve the original file and processing logs, notify the responsible legal and security owners, and review whether the manipulation influenced any downstream output. The response should focus on containment, evidence preservation, and revalidation of any AI-generated result.
👉 Read our full editorial: Prompt injection in court filings exposes AI review governance gaps