Improving LLM-Based SSH Honeypots through Prompting and Fine-Tuning

LLM-based SSH honeypots often use closed cloud LLMs because they give strong shell realism, but cloud models create deployment problems. These include no stable versioning, provider-side changes, attacker-driven cost, and model decommissioning. Local open-weight models avoid these problems, but...

PT-2026-80655

Summary confluence upload attachment passes file path directly to openfile path, "rb" with no path validation. Any authenticated MCP client — or an AI agent manipulated via prompt injection — can read any file the server process can access and exfiltrate it to Confluence as an attachment. Details...

CVE-2026-75130

Context7 through 2.1.2 contains a prompt injection vulnerability that allows attackers to execute malicious instructions in connected AI coding agents by injecting unsanitized content through the Custom AI Instructions feature served via the MCP server. Attackers can poison the custom instruction...

CVE-2026-75130 Context7 2.1.2 Prompt Injection via Custom AI Instructions

Context7 through 2.1.2 contains a prompt injection vulnerability that allows attackers to execute malicious instructions in connected AI coding agents by injecting unsanitized content through the Custom AI Instructions feature served via the MCP server. Attackers can poison the custom instruction...

CVE-2026-75130

Context7 through 2.1.2 has a prompt injection flaw in its Custom AI Instructions feature served via the MCP server. Attackers poison unsanitized instructions to exfiltrate credentials from environment files and delete files on victim machines when the agent makes routine documentation requests. C...

EUVD-2026-61099

Context7 through 2.1.2 contains a prompt injection vulnerability that allows attackers to execute malicious instructions in connected AI coding agents by injecting unsanitized content through the Custom AI Instructions feature served via the MCP server. Attackers can poison the custom instruction...

CVE-2026-75913

CodeWhale codewhale / codewhale-tui versions = 0.8.41 and 0.8.64 contain an argument injection vulnerability in the gitshow tool. The model-supplied rev parameter is passed unvalidated into the git show argv without an --end-of-options sentinel, so a value beginning with --output= is interpreted ...

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 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-2026-75913 CodeWhale before 0.8.64 Argument Injection via git_show

CodeWhale codewhale / codewhale-tui versions = 0.8.41 and 0.8.64 contain an argument injection vulnerability in the gitshow tool. The model-supplied rev parameter is passed unvalidated into the git show argv without an --end-of-options sentinel, so a value beginning with --output= is interpreted ...

CVE-2026-75913

CodeWhale versions 0.8.41–0.8.63 pass an unvalidated model-supplied rev parameter directly to git show argv without an --end-of-options sentinel, allowing a --output= value to be interpreted as a git flag. Combined with the auto-approved, read-only git_show tool and prompt injection, this enables...

CVE-2026-75913 CodeWhale before 0.8.64 Argument Injection via git_show

CodeWhale codewhale / codewhale-tui versions = 0.8.41 and 0.8.64 contain an argument injection vulnerability in the gitshow tool. The model-supplied rev parameter is passed unvalidated into the git show argv without an --end-of-options sentinel, so a value beginning with --output= is interpreted ...

CVE-2026-75913 CodeWhale before 0.8.64 Argument Injection via git_show

CodeWhale codewhale / codewhale-tui versions = 0.8.41 and 0.8.64 contain an argument injection vulnerability in the gitshow tool. The model-supplied rev parameter is passed unvalidated into the git show argv without an --end-of-options sentinel, so a value beginning with --output= is interpreted ...

CVE-2026-75913

CodeWhale codewhale / codewhale-tui versions = 0.8.41 and 0.8.64 contain an argument injection vulnerability in the gitshow tool. The model-supplied rev parameter is passed unvalidated into the git show argv without an --end-of-options sentinel, so a value beginning with --output= is interpreted ...

CVE-2026-75858

In CodeWhale (codewhale/codewhale-tui) versions 0.8.41–0.8.63, rlm_eval's approval_requirement() returns ApprovalRequirement::Auto, causing the engine to execute arbitrary model-supplied Python code without consulting the user's --approval-policy or prompting for approval. An attacker can trigger...

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-2026-75858 CodeWhale rlm_eval before 0.8.64 Remote Code Execution

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 fails to validate file paths in the project config instructions field. A malicious .codewhale/config.toml in a cloned repo can read files outside the workspace and inject their contents into the AI system prompt, enabling exfiltration. CVSS 7.5 HIGH. Patch released; no kno...

CVE-2026-75858 CodeWhale rlm_eval before 0.8.64 Remote Code Execution

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-2026-75858 CodeWhale rlm_eval before 0.8.64 Remote Code Execution

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...