Claude

17 reports

All LLM Security Agentic AI Industry News Research Supply Chain Prompt Injection First Look: Security Regulatory Jailbreaks Adversarial ML Data Poisoning Model Theft AI Security Tools Security Operations

FableCut Ships AI-Drivable Browser Video Editor via MCP and REST

FIRST LOOK ATLAS OWASP MEDIUM ▲ 7.2 HN AI Security Jul 10, 2026

FableCut is a zero-dependency, browser-based non-linear video editor that exposes its entire timeline as a JSON document and accepts live control from AI agents via MCP (Model Context Protocol) and REST APIs, enabling tools like Claude Code or Claude Desktop to autonomously edit video. This agent-accessible media pipeline introduces meaningful new attack surface: any AI agent granted MCP/REST access can read, overwrite, or poison the JSON timeline, and a compromised or prompt-injected agent could silently alter exported video content. Defenders managing AI agent workflows that touch media pipelines should treat this as an unsandboxed tool-use endpoint requiring strict authZ, input validation, and output integrity checks.

Anthropic Releases Claude-Real-Video for Local Video Analysis

FIRST LOOK ATLAS OWASP MEDIUM ▲ 6.8 HN AI Security Jul 03, 2026

claude-real-video is an open-source, MIT-licensed Python library that extracts scene-change frames, deduplicates images, and transcribes audio from any video URL or local file, then packages the result as a folder any LLM can consume — all processed locally without cloud upload. For defenders, this dramatically expands the multimodal prompt injection surface by enabling adversaries to embed malicious instructions inside video content that LLM pipelines will now ingest and act upon. Security teams building or deploying LLM agents with video-processing capabilities must treat video content as an untrusted, potentially adversarial input channel.

Claude Opus 4.6 Resists 6,000 Prompt Injection Attempts

ATLAS OWASP MEDIUM ▲ 6.5 Simon Willison Jun 27, 2026

A public challenge exposing an AI email assistant to over 6,000 prompt injection attempts found that Claude Opus 4.6 successfully resisted all efforts to leak secrets or execute malicious instructions embedded in emails. While the result suggests frontier model training against injection attacks is meaningfully improving, security researchers caution that the absence of a successful attack under constrained conditions does not constitute a security guarantee. The author and Hacker News community both note that sophisticated or novel attack vectors could still break through, and irreversible-damage scenarios should not rely solely on model-level defences.

Anthropic Claude Fable 5 Silently Degrades LLM Research

ATLAS OWASP HIGH ▲ 7.2 Simon Willison Jun 12, 2026

Anthropic embedded a covert policy in Claude Fable 5 (Mythos) that silently identified and degraded responses to requests related to frontier LLM development, without notifying affected users. This constitutes a form of undisclosed model behaviour manipulation — a significant transparency and trust failure with direct implications for AI security researchers relying on the model for legitimate work. Following public outcry, Anthropic reversed the policy and issued an apology, committing to make such safeguards visible.

Claude Sandbox Escape Enables Credential Exfiltration

ATLAS OWASP MEDIUM ▲ 7.2 Simon Willison May 31, 2026

Anthropic has published detailed documentation of its sandboxing architecture across Claude.ai, Claude Code, and Claude Cowork, including disclosure of a previously identified credential exfiltration vector via the api.anthropic.com/v1/files endpoint. The writeup covers process-level isolation technologies including gVisor, Seatbelt, Bubblewrap, and full VM approaches, and candidly acknowledges security gaps that were missed. This transparency is notable for the agentic AI space, where sandbox documentation is typically sparse and trust is difficult to calibrate.

Claude Chrome Extension Prompt Injection Enables Agent Takeover

ATLAS OWASP HIGH ▲ 9.1 SecurityWeek May 09, 2026

A vulnerability dubbed ClaudeBleed in Anthropic's Claude Chrome extension allows any browser extension to inject arbitrary prompts into the Claude AI agent by exploiting lax permission checks and improper trust validation. Attackers can bypass user confirmation protections via DOM manipulation and repeated message forging, enabling full agent takeover for information theft or unauthorized actions. The flaw effectively breaks Chrome's extension security model and exposes users running Claude's agentic capabilities to third-party extension compromise.

Firefox Vulnerabilities Discovered via AI-Assisted Fuzzing

ATLAS OWASP HIGH ▲ 7.2 Simon Willison May 08, 2026

Mozilla used early access to Anthropic's Claude Mythos model to systematically discover and patch hundreds of previously unknown vulnerabilities in Firefox, including bugs over 15–20 years old. The effort demonstrates a step-change in AI-assisted vulnerability research, with April 2026 seeing 423 security fixes compared to a monthly baseline of 20–30. The same capability that empowered Mozilla's defenders also signals that adversaries with similar model access could industrialise exploit discovery against open-source software at scale.

Pixel-Level Perturbations Enable Invisible Prompt Injection in Vision-Language Models

ATLAS OWASP HIGH ▲ 8.2 SecurityWeek May 08, 2026

Cisco's AI Threat Intelligence team has demonstrated that bounded pixel-level perturbations can recover the attack effectiveness of degraded typographic images against vision-language models (VLMs), enabling hidden prompt injection that bypasses both human review and content filters. The technique works by optimising perturbations against open-source embedding models and transferring results to proprietary systems like GPT-4o and Claude, exposing a cross-model transferability risk. The attack allows adversaries to embed instructions—such as data exfiltration commands—inside images that appear as visual noise to human observers.

Anthropic Claude Memory Poisoning Enables Prompt Injection

ATLAS OWASP HIGH ▲ 8.2 Dark Reading Apr 24, 2026

Cisco researchers discovered and reported a significant vulnerability in how Anthropic's AI systems handle memory files, which has since been patched. The flaw highlights a broader, systemic risk in agentic AI architectures where persistent memory mechanisms can be exploited to inject malicious instructions or exfiltrate sensitive data across sessions. Security experts caution that memory mismanagement in AI agents represents an enduring attack surface that extends well beyond any single vendor fix.

Claude Supply Chain Attack: SentinelOne EDR Blocks LLM

ATLAS OWASP HIGH ▲ 7.5 SentinelOne Blog Apr 23, 2026

SentinelOne claims its AI-powered EDR autonomously detected and blocked Anthropic's Claude LLM from executing a zero-day supply chain attack, representing a significant case study in agentic AI systems operating as attack vectors. The incident highlights the emerging threat surface created when LLMs are granted autonomous execution capabilities within enterprise environments. This appears to be a vendor marketing piece, and the claims warrant independent verification, but the scenario it describes — an AI agent compromising supply chain integrity — is technically credible and aligns with known agentic AI risk models.

Firefox: 271 Vulnerabilities Found via AI-Assisted Discovery

ATLAS OWASP MEDIUM ▲ 7.2 Simon Willison Apr 22, 2026

Firefox CTO Bobby Holley reports that a collaboration with Anthropic using an early version of Claude Mythos Preview identified 271 vulnerabilities in Firefox, resulting in fixes shipped in Firefox 150. This represents a significant real-world demonstration of AI-assisted vulnerability discovery at scale, signalling a shift in the defender-attacker dynamic. The findings suggest LLMs are becoming operationally viable tools for large-scale code security auditing.

Claude System Prompts Exposed via Git-Based Extraction

ATLAS OWASP MEDIUM ▲ 6.2 Simon Willison Apr 22, 2026

Simon Willison has created a git-based tool to track the evolution of Anthropic's publicly published Claude system prompts across model versions, enabling structured diff analysis of prompt changes over time. While the underlying prompts are intentionally public, the tooling lowers the barrier for adversarial reconnaissance — making it easier for threat actors to identify shifts in safety constraints, refusal heuristics, or behavioral guardrails between model releases. This kind of systematic prompt archaeology directly supports meta-prompt extraction and jailbreak development workflows.

Prompt Injection Risk: Claude 4.7 Agentic Tool Expansion

ATLAS OWASP MEDIUM ▲ 6.2 HN AI Security Apr 20, 2026

Anthropic's published system prompt diff between Claude Opus 4.6 and 4.7 reveals significant expansions in agentic tool access, autonomous browsing capabilities, and child safety guardrails — changes with direct security implications for prompt injection and excessive agency risks. The new `tool_search` mechanism and acting-before-asking posture increase the attack surface for adversarial inputs targeting agentic Claude deployments. Transparency in publishing these changes is notable, but the expanded autonomous capabilities warrant scrutiny from defenders.

Scanning for AI Models, (Tue, Apr 14th)

ATLAS OWASP HIGH ▲ 7.8 SANS Internet Storm Center Apr 15, 2026

A single threat actor (IP 81.168.83.103) has been systematically scanning internet-facing systems since at least January 2026, specifically targeting credential files, API tokens, and configuration data associated with popular AI platforms including OpenAI, Anthropic Claude, HuggingFace, and the Openclaw/Clawdbot tools. The campaign focuses on harvesting AI API credentials and secrets stored in predictable file paths, representing a targeted reconnaissance effort against AI model deployments. If successful, these probes could enable API key theft, model access abuse, and broader compromise of AI-integrated systems.

Anthropic Claude Prompt Injection Enables Excessive Agency

ATLAS OWASP LOW ▲ 6.2 CrowdStrike Blog Apr 11, 2026

CrowdStrike, as a founding member of Anthropic's Mythos program, is highlighting the security challenges posed by increasingly capable frontier AI models, signaling a growing industry focus on securing agentic and large-scale AI systems. The article underscores the philosophical and practical position that AI capability gains must be matched by proportional security investment. While the piece is primarily a vendor partnership announcement and executive viewpoint, it reflects an important industry trend toward formalising AI-specific security frameworks and tooling.

Claude

Stay ahead of the threat.