10 matches found
CVE-2026-54140 OpenHuman: MCP tool description injection: untrusted server descriptions execute in agent LLM context without sanitization
OpenHuman is an open-source agent harness available as a desktop application and Rust library. Before 0.57.13, OpenHuman places names, descriptions, titles, and parameter definitions returned by configured external MCP servers into the agent model context without neutralizing instructions or...
CVE-2026-54140
The OpenHuman agent harness (desktop application and Rust library) is vulnerable to MCP tool description injection prior to version 0.57.13 . The application fails to neutralize or bound names, descriptions, titles, and parameter definitions returned by external MCP servers when placing them into...
CVE-2026-54140 OpenHuman: MCP tool description injection: untrusted server descriptions execute in agent LLM context without sanitization
OpenHuman is an open-source agent harness available as a desktop application and Rust library. Before 0.57.13, OpenHuman places names, descriptions, titles, and parameter definitions returned by configured external MCP servers into the agent model context without neutralizing instructions or...
CVE-2026-27165
Attackers who can influence ACP "resourcelink" metadata can inject attacker-controlled prompt text into the LLM context, potentially altering model behavior...
Decepticon: Role-boundary forgery via ChatML special-token literals in web crawl output composed into LLM context
SummaryDecepticon wraps web crawl results — the output of agent reconnaissance against target services — into LLM messages without neutralizing ChatML special-token literals. Under the BYOK Bring Your Own Key deployment model, users configure their own LLM credentials to any OpenAI-compatible...
CVE-2026-45792
Vulnerability summary (CVE-2026-45792) RTK (Rust Token Killer) prior to 0.32.0 trusts project-local configuration by auto-loading the highest-priority .rtk/filters.toml without user notification. An attacker with repository access can place a malicious filter to modify shell command output before...
Malware in llm-context-compressor
Any computer that has this package installed or running should be considered fully compromised. All secrets and keys stored on that computer should be rotated immediately from a different computer. The package should be removed, but as full control of the computer may have been given to an outsid...
Malicious Package
Overview llm-context-compressor is a malicious package. This package contains malicious code, and its content was removed from the official package manager. While this package might be attempting to impersonate a valid organization, there is no connection between that organization and this packag...
MAL-2026-4278 Malicious code in llm-context-compressor (npm)
Ten packages published by npm user asdxzxc at version 1.0.10 target developers working on AI and LLM tooling. Each package masquerades as a developer utility while executing a two-stage payload triggered via postinstall: package.json → lib/setup.js → lib/worker.js. Credential harvesting:...
Malicious code in llm-context-compressor (npm)
Ten packages published by npm user asdxzxc at version 1.0.10 target developers working on AI and LLM tooling. Each package masquerades as a developer utility while executing a two-stage payload triggered via postinstall: package.json → lib/setup.js → lib/worker.js. Credential harvesting:...