Lucene search
+L

801 matches found

HackRead
HackRead
added 2026/04/09 1:50 p.m.8 views

Claude Code Can Be Manipulated via CLAUDE.md to Run SQL Injection Attacks

LayerX researchers have discovered how to bypass Claude Code’s safety rules using the CLAUDE.md file. This exploit allows…...

5.9AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2026/04/09 12:0 a.m.7 views

Vulnerability Detection with Interprocedural Context in Multiple Languages: Assessing Effectiveness and Cost of Modern LLMs

Large Language Models LLMs have been a promising way for automated vulnerability detection. However, most prior studies have explored the use of LLMs to detect vulnerabilities only within single functions, disregarding those related to interprocedural dependencies. These studies overlook...

5.8AI score
SaveExploits0
The Hacker News
The Hacker News
added 2026/04/08 9:16 a.m.13 views

Anthropic's Claude Mythos Finds Thousands of Zero-Day Flaws Across Major Systems

Artificial Intelligence AI company Anthropic announced a new cybersecurity initiative called Project Glasswing that will use a preview version of its new frontier model, Claude Mythos , to find and address security vulnerabilities. The model will be used by a small set of organizations, including...

6AI score
SaveExploits0
Github Security Blog
Github Security Blog
added 2026/04/08 12:16 a.m.7 views

openclaw-claude-bridge: sandbox is not effective - `--allowed-tools ""` does not restrict available tools

Affected openclaw-claude-bridge v1.1.0 Issue v1.1.0 spawns the Claude Code CLI subprocess with --allowed-tools "" and the release notes + README claim this "disables all CLI tools" for sandboxing. This claim is incorrect. Per the Claude Code CLI documentation, --allowed-tools alias --allowedTools...

6.3AI score
SaveExploits0References4Affected Software1
OSV
OSV
added 2026/04/08 12:16 a.m.13 views

GHSA-7853-GQQM-VCWX openclaw-claude-bridge: sandbox is not effective - `--allowed-tools ""` does not restrict available tools

Affected openclaw-claude-bridge v1.1.0 Issue v1.1.0 spawns the Claude Code CLI subprocess with --allowed-tools "" and the release notes + README claim this "disables all CLI tools" for sandboxing. This claim is incorrect. Per the Claude Code CLI documentation, --allowed-tools alias --allowedTools...

6.1AI score
SaveExploits0References4
Positive Technologies
Positive Technologies
added 2026/04/08 12:0 a.m.16 views

PT-2026-31279

Affected openclaw-claude-bridge v1.1.0 Issue v1.1.0 spawns the Claude Code CLI subprocess with --allowed-tools "" and the release notes + README claim this "disables all CLI tools" for sandboxing. This claim is incorrect. Per the Claude Code CLI documentation, --allowed-tools alias --allowedTools...

6.3AI score
SaveExploits0References5
RedhatCVE
RedhatCVE
added 2026/04/07 11:1 p.m.7 views

CVE-2026-35021

Anthropic Claude Code CLI and Claude Agent SDK contain an OS command injection vulnerability in the prompt editor invocation utility that allows attackers to execute arbitrary commands by crafting malicious file paths. Attackers can inject shell metacharacters such as $ or backtick expressions in...

8.4CVSS6.2AI score0.00041EPSS
SaveExploits0References1
RedhatCVE
RedhatCVE
added 2026/04/07 11:1 p.m.8 views

CVE-2026-35020

Anthropic Claude Code CLI and Claude Agent SDK contain an OS command injection vulnerability in the command lookup helper and deep-link terminal launcher that allows local attackers to execute arbitrary commands by manipulating the TERMINAL environment variable. Attackers can inject shell...

8.6CVSS6.2AI score0.00114EPSS
SaveExploits0References1
Wired Threat Level
Wired Threat Level
added 2026/04/07 6:49 p.m.7 views

Anthropic Teams Up With Its Rivals to Keep AI From Hacking Everything

The AI lab's Project Glasswing will bring together Apple, Google, and more than 45 other organizations. They'll use the new Claude Mythos Preview model to test advancing AI cybersecurity capabilities...

5.9AI score
SaveExploits0
Trend Micro Simply Security
Trend Micro Simply Security
added 2026/04/07 12:0 a.m.6 views

Claude Code Packaging Error Remains a Lure in an Active Campaign: What Defenders Should Do

Threat actors leveraged Anthropic’s Claude Code npm release packaging error to distribute Vidar, GhostSocks, and PureLog Stealer. This blog details immediate steps organizations can take and best practices to prevent further risk...

5.9AI score
SaveExploits0
RedhatCVE
RedhatCVE
added 2026/04/06 10:59 p.m.7 views

CVE-2025-64340

FastMCP is the standard framework for building MCP applications. Prior to version 3.2.0, server names containing shell metacharacters e.g., & can cause command injection on Windows when passed to fastmcp install claude-code or fastmcp install gemini-cli. These install paths use subprocess.run wit...

7.8CVSS5.8AI score0.00749EPSS
SaveExploits1References1
EUVD
EUVD
added 2026/04/06 9:31 p.m.12 views

EUVD-2026-19438

Anthropic Claude Code CLI and Claude Agent SDK contain an OS command injection vulnerability in the command lookup helper and deep-link terminal launcher that allows local attackers to execute arbitrary commands by manipulating the TERMINAL environment variable. Attackers can inject shell...

8.6CVSS6.2AI score0.00114EPSS
SaveExploits0References3
EUVD
EUVD
added 2026/04/06 9:31 p.m.9 views

EUVD-2026-19440

Anthropic Claude Code CLI and Claude Agent SDK contain an OS command injection vulnerability in the prompt editor invocation utility that allows attackers to execute arbitrary commands by crafting malicious file paths. Attackers can inject shell metacharacters such as $ or backtick expressions in...

8.4CVSS6.2AI score0.00041EPSS
SaveExploits0References3
NVD
NVD
added 2026/04/06 8:16 p.m.9 views

CVE-2026-35021

Rejected reason: This CVE ID has been rejected by its CVE Numbering Authority CNA. It was determined that the affected code path cannot be triggered through normal usage of Claude Code...

0.00041EPSS
SaveExploits0
NVD
NVD
added 2026/04/06 8:16 p.m.9 views

CVE-2026-35020

Rejected reason: This CVE ID has been rejected by the its CVE Numbering Authority CNA. It was determined that the attack requires an attacker to already control arbitrary environment variables, a level of access they consider functionally equivalent to code execution and outside the threat model ...

0.00114EPSS
SaveExploits0
Cvelist
Cvelist
added 2026/04/06 6:59 p.m.29 views

CVE-2026-35022

...

0.00596EPSS
SaveExploits0
CVE
CVE
added 2026/04/06 6:59 p.m.23 views

CVE-2026-35022

Anthropic Claude Code CLI and Claude Agent SDK are cited in multiple sources as vulnerable to an OS command injection in authentication helper execution. The underlying issue is that helper configuration values are executed with shell=true without input validation, allowing injection of shell met...

6.2AI score0.00596EPSS
SaveExploits0
Vulnrichment
Vulnrichment
added 2026/04/06 6:59 p.m.4 views

CVE-2026-35022

...

5.8AI score0.00596EPSS
SaveExploits0
ATTACKERKB
ATTACKERKB
added 2026/04/06 6:59 p.m.3 views

CVE-2026-35022

This CVE ID has been rejected by its CVE Numbering Authority CNA. It was determined that the -p flag behavior is documented in Anthropic's claude -h output with an explicit warning that non-interactive mode should only be used in trusted directories, making this intended and described behavior...

5.7AI score0.00596EPSS
SaveExploits0References3
Vulnrichment
Vulnrichment
added 2026/04/06 6:59 p.m.5 views

CVE-2026-35021

...

5.8AI score0.00041EPSS
SaveExploits0
Rows per page
Query Builder