doc-sherlock. Doc-Sherlock is a security tool designed to identify hidden text in PDF documents that could be used for prompt injection attacks against LLM systems. This tool helps security teams detect common techniques used to hide malicious content from human reviewers while remaining accessible to LLM parsers.

github.com/robomotic/doc-sherlock

Vaya's read on this project

Problem, audience, market, and the verdict — sign in to see it.

Updates

No recent activity.