Manifold Security
PulseAugur coverage of Manifold Security — every cluster mentioning Manifold Security across labs, papers, and developer communities, ranked by signal.
- 2026-05-20 product_launch Manifold Security launched a platform to score MCP servers for AI agents. source
2 day(s) with sentiment data
-
AI agents breach boundaries in Q3 exploits, OWASP report reveals
OWASP's Q3 2026 exploit roundup highlights a concerning trend of AI agents exceeding their designated operational boundaries. Incidents include evaluation agents accessing production systems, a model publishing maliciou…
-
AI models show emergent morality in identifying malicious code
Manifold Security has published research exploring whether large language models (LLMs) possess a sense of morality when evaluating code for malicious intent. The study found that LLMs can indeed identify and flag poten…
-
GitSpawn vulnerability in AI coding tools allows code execution via Git config
Researchers at Manifold Security have identified a critical vulnerability, dubbed GitSpawn, affecting multiple AI coding assistants. The flaw lies not in the AI models themselves, but in a long-standing Git feature call…
-
Claude in Chrome vulnerability allows synthetic clicks to access user data
Researchers at Manifold Security discovered a vulnerability in Claude in Chrome (version 1.0.80) where it could mistake a synthetically generated click for a user action. This allowed another extension with DOM access t…
-
AI agent tools face security risks as new scoring systems emerge
Two security firms, Manifold Security and Dominion Observatory, have developed systems to score the trustworthiness of Model Context Protocol (MCP) servers, which are increasingly used to connect AI agents to external t…