CVE-2026-75858

CodeWhale packages codewhale / codewhale-tui versions = 0.8.41 and 0.8.64 contain a remote code execution vulnerability in the rlmeval tool. The tool's approvalrequirement returns ApprovalRequirement::Auto, which the engine treats as 'never prompt,' causing arbitrary model-supplied Python code to...

CVE-2026-75859 CodeWhale before 0.8.64 Arbitrary File Read via instructions

CodeWhale versions before 0.8.64 fail to validate file paths in the project config instructions field, allowing attackers to read arbitrary files on the victim's system. A malicious .codewhale/config.toml file in a cloned repository can specify paths outside the workspace that are read and inject...

CVE-2026-75859 CodeWhale before 0.8.64 Arbitrary File Read via instructions

CodeWhale versions before 0.8.64 fail to validate file paths in the project config instructions field, allowing attackers to read arbitrary files on the victim's system. A malicious .codewhale/config.toml file in a cloned repository can specify paths outside the workspace that are read and inject...

AI "Mind Viruses" Can Spread Between Agents Through Persistent Prompt Files

Security researchers at Anthropic and Switzerland's EPFL have demonstrated that self-propagating payloads can spread from one artificial intelligence AI agent to the next through the editable system prompt files that autonomous agent harnesses use to carry state between sessions. The work, releas...

PT-2026-77160

Name of the Vulnerable Software and Affected Versions CodeWhale versions prior to 0.8.64 Description Insufficient validation of file paths in the project config instructions field allows for the reading of arbitrary files on a system. An attacker can use a malicious .codewhale/config.toml file...

PT-2026-77164

Name of the Vulnerable Software and Affected Versions CodeWhale versions 0.8.41 through 0.8.63 Description An argument injection issue exists in the git show tool. The rev parameter is passed unvalidated into the git show argument vector without an --end-of-options sentinel, allowing a value...

PT-2026-77159

Name of the Vulnerable Software and Affected Versions CodeWhale versions 0.8.41 through 0.8.63 Description A remote code execution issue exists in the rlm eval tool. The approval requirement function returns ApprovalRequirement::Auto, which the engine interprets as a command to never prompt the...

CVE-2026-75483

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...

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...

CVE-2026-75483

powerlevel10k fails to sanitize control characters in the package.json version field when rendering the package prompt segment, allowing an attacker to embed raw escape bytes that emit arbitrary terminal control sequences on each prompt render when a user enters a compromised directory. CVSS 3.1 ...

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...

EUVD-2026-60395

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...

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

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

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...

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

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

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...