Lucene search
+L

10 matches found

osv_cve
osv_cve
•added 2026/11/05 4:13 p.m.•19 views

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...

8.3CVSS5.9AI score
SaveExploits0References6
CVE
CVE
•added 2026/11/05 4:13 p.m.•25 views

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...

8.3CVSS5.9AI score0.00554EPSS
SaveExploits0References4
Cvelist
Cvelist
•added 2026/11/05 4:13 p.m.•31 views

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...

8.3CVSS0.00554EPSS
SaveExploits0References4
Mend
Mend
•added 2026/10/12 11:52 a.m.•18 views

CVE-2026-27165

Attackers who can influence ACP "resourcelink" metadata can inject attacker-controlled prompt text into the LLM context, potentially altering model behavior...

6.1CVSS5.8AI score0.00086EPSS
SaveExploits0References3
PyPA
PyPA
•added 2026/10/01 4:38 p.m.•47 views

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...

10CVSS6.9AI score0.0147EPSS
SaveExploits1References8Affected Software1
CVE
CVE
•added 2026/06/23 7:02 p.m.•85 views

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...

6.9CVSS5.9AI score0.0011EPSS
SaveExploits0References3Affected Software1
Github Security Blog
Github Security Blog
•added 2026/05/24 3:36 p.m.•5 views

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...

5.8AI score
SaveExploits0References1Affected Software1
Snyk
Snyk
•added 2026/05/24 3:36 p.m.•26 views

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...

9.8CVSS5.8AI score
SaveExploits0References2
osv_mal
osv_mal
•added 2026/05/23 12:00 a.m.•32 views

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:...

6AI score
SaveExploits0References7
OSSF Malicious Packages
OSSF Malicious Packages
•added 2026/05/23 12:00 a.m.•28 views

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:...

6AI score
SaveExploits0References7
Rows per page
Query Builder