CVE-2026-75483 powerlevel10k Control Character Injection via package.json Version

powerlevel10k fails to neutralize control characters in the package.json version field when rendering the package prompt segment. Attackers can inject raw escape bytes in the version string to emit arbitrary terminal control sequences on each prompt render when the shell enters affected directori...

ANT-2026-6JWE6ZK7 · langchain-ai/deepagentsjs · sandbox_escape

other high Severity Claude high · Security research firm high · Maintainer - Discovered by Claude Mythos Preview REPORT Anthropic's analysis, sealed at approval. Disclosure to the maintainer was performed by Anvil Security. ANT-2026-6JWE6ZK7: VFS sandbox executes agent commands directly on host T...

How MCP Servers Can Expose Enterprise Secrets

MCP servers can expose enterprise secrets through plaintext configuration files, over-permissioned access and prompt injection, often before security teams even know the server is running. As more organizations adopt AI agents into their systems, that exposure can silently become a major gap in M...

BIT-GITLAB-2026-15077 Improper Neutralization of Input Used for LLM Prompting in GitLab

GitLab has remediated an issue in GitLab EE affecting all versions from 19.1 before 19.1.3 and 19.2 before 19.2.1 that under certain conditions could have allowed an authenticated user to access information from unauthorized projects due to improper neutralization of untrusted content processed b...

augustus v0.14.20

Augustus - LLM vulnerability scanner for prompt injection, jailbreak, and adversarial attack testing Augustus - LLM Vulnerability Scanner Test large language models against 210+ adversarial attacks covering prompt injection, jailbreaks, encoding exploits, and data extraction. Augustus is a Go-bas...

[SECURITY] Fedora 43 Update: rust-pretty-git-prompt-0.2.2-11.fc43

Your current git repository information inside a beautiful shell prompt...

DSPrompt: Dynamic Soft Prompt Defense against M-RAG Corruption

Multimodal Retrieval Augmented Generation M-RAG is increasingly vulnerable to adversarial attacks where malicious data are crafted to produce embeddings that align with benign entries in the vector space, deceiving retrieval and inducing harmful outputs. Existing defenses primarily operate at que...

PT-2026-76810

Name of the Vulnerable Software and Affected Versions powerlevel10k affected versions not specified Description The software fails to neutralize control characters within the version field of a package.json file when rendering the package prompt segment. This allows an attacker to inject raw esca...

CVE-2026-75483: Improper Neutralization of Escape, Meta, or Control Sequences

powerlevel10k fails to neutralize control characters in the package.json version field when rendering the package prompt segment. Attackers can inject raw escape bytes in the version string to emit arbitrary terminal control sequences on each prompt render when the shell enters affected directori...

[SECURITY] Fedora 44 Update: rust-pretty-git-prompt-0.2.2-11.fc44

Your current git repository information inside a beautiful shell prompt...

Benchmarking Identity-Sensitive LLM Outputs for Surveillance and Security Robots

Large language models LLMs are increasingly used to generate textual robot design specifications, interaction policies, and risk assessments during early-stage robot development. Such outputs may influence how surveillance and security robots are conceptualized, documented, and ultimately...

Bounded Agents: Delegation Security for Multi-Agent AI Systems

LLM-based agents can act on behalf of a user to access cloud services, call tools, or invoke agents. At session start, the agent's permissions are set but remain static, and each request is evaluated independently, without considering prior actions. Within its permissions, an agent may act contra...

CVE-2026-73506

A flaw was found in Oh My Posh, a customizable terminal prompt renderer. The software failed to properly sanitize attacker-controlled data, such as current directory names and Git metadata, before displaying it in the terminal. This oversight allows for terminal escape sequence injection, enablin...

CVE-2026-73559

A flaw was found in vLLM, an inference and serving engine for large language models. An authenticated API client can exploit this vulnerability by sending a single request to the /v1/completions endpoint with an excessively large list of prompts. This unbounded input causes the vLLM server to...

Workspace Topology As an Attack Vector in Agentic Coding Assistants

Agentic coding assistants are finding widespread use, not just in new code development but in quickly ingesting and leveraging third-party code. This opens up a risk of malicious code being ingested as these coding tools operate with broad filesystem access inside developer workspaces. In this...

vLLM: Completion prompt lists fan out into unbounded engine requests

Summary The /v1/completions request model accepts prompt as a list of text prompts or a list of token-id prompts without any outer prompt-count bound. The serving path turns each element into a separate engine input, creates one engine generator per element, merges all generators, and allocates a...

GHSA-87X5-VMC3-756J vLLM: Completion prompt lists fan out into unbounded engine requests

Summary The /v1/completions request model accepts prompt as a list of text prompts or a list of token-id prompts without any outer prompt-count bound. The serving path turns each element into a separate engine input, creates one engine generator per element, merges all generators, and allocates a...

sage v0.12.0

Sage Safety for Agents — Agent Detection & Response for AI coding assistants Sage is a lightweight security layer that protects AI agents from executing dangerous actions. It intercepts tool calls — shell commands, URL fetches, file writes — and checks them against multiple threat detection layer...

CVE-2026-73559

vLLM is an inference and serving engine for large language models. From 0.19.0 until 0.26.0, the /v1/completions CompletionRequest.prompt field in vllm/entrypoints/openai/completion/protocol.py accepts an unbounded liststr or listlistint, prompttoseq in vllm/renderers/inputs/preprocess.py and...

CVE-2026-73557

vLLM is an inference and serving engine for large language models. From 0.20.2rc0 until 0.26.0, safeloadpromptembeds in vllm/renderers/embedutils.py uses torch.sparse.checksparsetensorinvariants, whose process-global save, enable, and restore state can be raced by concurrent promptembeds parts...