» Tag
prompt-injection
35 postsSelf-Propagating AI Worm Found in Microsoft Copilot for Word
Researcher discloses self-propagating prompt injection worm in Microsoft Copilot for Word, unresolved after 144 days of coordinated disclosure.
Securing MCP Servers: Four Gates From Code to Production
A leaked .env file exposed a design flaw in an MCP server. Here's a four-gate, OWASP-aligned defense strategy engineers can adopt today.
OpenClaw WhatsApp Flaw: Three GHSA Bugs Turn One Message Into Host RCE
Three GHSA-tracked flaws in OpenClaw's WhatsApp integration let a single message trigger full host code execution; all fixed in version 2026.6.6.
CommitBrief — AI code reviews, right in your terminal
A provider-agnostic, local-first CLI that reviews your staged changes, a historic range, or a whole GitHub pull request. Zero telemetry, no server. Free and open source.
commitbrief.comSynapsor Runner Lets AI Agents Propose Changes, Not Execute SQL
Synapsor Runner is an open-source MCP runtime giving AI agents reviewed semantic tools instead of raw SQL, keeping database write authority outside the model loop.
agent-gate: keep your AI agents from having unchecked power
agent-gate is a dependency-free MIT Python layer that gates AI agent actions behind deterministic checks and one-time tokens, blocking prompt injection and irreversible mistakes.
How homoglyph attacks slip past LLM guardrail filters
Jailbreak prompts written with Cyrillic and Greek look-alike characters easily bypass naive keyword filters. The fix: normalize text before matching, not after.
HalluSquatting: How AI Coding Agents Turn Into a Botnet
AI coding tools like Cursor, Copilot, and Gemini CLI can hallucinate package names that attackers pre-register with malware, turning normal agent use into silent compromise.
New Attack Class: Agent Data Injection (ADI) in AI Agents
Researchers uncovered a new attack class that tricks AI agents via fake trusted metadata, exposing critical vulnerabilities in Claude, Codex, and Gemini CLI agents.
Agent Control Plane: The LLM Proposes, It Never Authorizes
Agent Control Plane keeps AI agent authorization outside the model, blocking prompt injection with signed policy and human sign-off for risky actions.
Researcher Tricks Claude Into Leaking User Secrets via Web Fetch
How a researcher exploited Claude's memory and web_fetch tool to silently exfiltrate a user's name, employer, and security answers letter by letter.