Unicode
PulseAugur coverage of Unicode — every cluster mentioning Unicode across labs, papers, and developer communities, ranked by signal.
5 day(s) with sentiment data
-
Anthropic's Claude Code accused of steganography in system prompts
A developer has raised concerns that Anthropic's Claude Code, an AI tool with shell access, has been embedding invisible tracking signals within its system prompts using variations of Unicode apostrophes and date format…
-
Apple's Spotlight embraces semantic search for deeper understanding
Apple's Spotlight search is evolving to incorporate semantic search capabilities, moving beyond simple keyword matching to understand the meaning and context of search terms. This new approach, highlighted at the recent…
-
New font renders QR codes directly from text input
A developer has created a TrueType font that renders QR codes directly from bracketed text. This font, named Jim's TrueType QR Code Font, utilizes OpenType rules to transform text like '[hello]' into a QR code without r…
-
Biomedical APIs show inconsistent Unicode fidelity, impacting LLM training data
A recent audit of four major biomedical bibliographic APIs—PubMed E-utilities, Crossref, OpenAlex, and Semantic Scholar—revealed significant inconsistencies in how they handle Unicode characters. The study found that th…
-
AI agents vulnerable to malicious tool descriptions, new exploit reveals
A security vulnerability has been identified in how AI agents process tool descriptions, particularly within MCP servers. Malicious instructions can be embedded in the 'description' field of a tool manifest, which agent…
-
GitLab Duo prompt injection exploit highlights scanner blind spots
A prompt injection vulnerability was discovered in GitLab Duo, where malicious instructions could be hidden within project content using encoding techniques like Unicode smuggling and Base16. Researchers at Legit Securi…
-
New tool targets hidden Unicode attacks in AI code
A new tool called `claude-code-plugins` has been developed to address security vulnerabilities in AI-generated code, specifically targeting supply-chain attacks. The tool identifies malicious instructions hidden within …
-
New RAG-Pull attack exploits LLMs via invisible Unicode characters
Researchers have developed a novel attack method called RAG-Pull that exploits Retrieval-Augmented Generation (RAG) systems. By inserting invisible Unicode characters into queries or external code, RAG-Pull can redirect…
-
Developer releases Velio tool to combat hidden prompt injection attacks
A developer has created an open-source tool named Velio to combat prompt injection attacks by sanitizing text input for large language models. The tool identifies and removes or marks specific Unicode characters, such a…