VulnWatch VulnWatch
← Back to dashboard
#

Prompt Injection

231 entries

Every Prompt Injection entry VulnWatch has indexed, sorted by publication date.

Subscribe to this tag's RSS feed

Medium github

MCP Atlassian: Arbitrary File Read via Upload Attachment Tools

## Summary The upload attachment tools in both Confluence and Jira accept arbitrary file paths without path traversal validation. The upload_attachment methods read any file accessible to the server...

Prompt Injection prompt injection
6.5
CVSS
1 month ago
High github

MCP Atlassian: Arbitrary local file READ via unconstrained file_path in upload_attachment (Confluence + Jira)

## Summary This is an arbitrary local file READ vulnerability on the Confluence and Jira `upload_attachment` tool paths. It's the symmetric counterpart of the file-write vulnerability you patched as...

Prompt Injection Agentic / MCP prompt injection mcp server llm agent llm
0.0
CVSS
1 month ago
Medium github

@aborruso/ckan-mcp-server has SSRF via DNS-name → internal IP — incomplete fix of CVE-2026-53509

## Summary The SSRF guard `validateServerUrl` (added for CVE-2026-33060, extended for CVE-2026-53509) validates only the **hostname string** and never resolves DNS. Any caller-supplied `server_url` wh...

Prompt Injection SSRF prompt injection
5.7
CVSS
1 month ago
High github

@roomi-fields/notebooklm-mcp has a path traversal in vault.batch tool that allows arbitrary file write outside intended vault directory

## Summary The `vault_batch` MCP tool (and the equivalent `POST /batch-to-vault` HTTP endpoint) accepted a caller-supplied `vault_dir` path that was passed directly to `path.resolve()` + `fs.mkdir()`...

Prompt Injection Agentic / MCP prompt injection mcp server llm
0.0
CVSS
1 month ago
Unknown rss_securityweek

AIUC Raises $40 Million to Certify Enterprise AI Agents

The company provides a standard for AI systems, testing them against risks such as jailbreaks, prompt injections, and unauthorized actions. The post AIUC Raises $40 Million to Certify Enterprise AI Ag...

Prompt Injection Agentic / MCP prompt injection jailbreak ai agent
2 months ago
High github

@zereight/mcp-gitlab has multiple safety-control bypasses: execute_graphql read-only + allow-list bypass, unauthenticated transports, session-exhaustion DoS

### Summary @zereight/mcp-gitlab exposes GitLab to an LLM agent while relying on read-only mode, a project allow-list, and transport auth as its safety controls. Five defects defeat those controls. Un...

Prompt Injection Agentic / MCP prompt injection replicate llm agent llm
8.1
CVSS
2 months ago
High nvd

CVE-2026-53957: Contentful MCP Server is a Model Context Protocol server for the Contentful Management API. Prior to @contentful/mcp-ser

Contentful MCP Server is a Model Context Protocol server for the Contentful Management API. Prior to @contentful/mcp-server 1.7.19 and @contentful/mcp-tools 0.4.5, export_space and import_space in pac...

Prompt Injection Agentic / MCP model context protocol prompt injection mcp server llm
7.7
CVSS
2 months ago
High github

functype-mcp-server: MCP `set_functype_version` Package Alias RCE via Unsanitized pnpm install + Dynamic Import

## MCP `set_functype_version` Package Alias RCE via Unsanitized pnpm install + Dynamic Import ### Summary The `set_functype_version` MCP tool in `functype-mcp-server` accepts an unconstrained `versi...

Prompt Injection Remote Code Execution Agentic / MCP prompt injection indirect prompt mcp server llm agent llm
7.8
CVSS
2 months ago
Low nvd

CVE-2026-85704: A security flaw has been discovered in ramon-victor freegpt-webui up to 098db3dfeb41555c2ca9269df0f13e10ec1c35dc. This i

A security flaw has been discovered in ramon-victor freegpt-webui up to 098db3dfeb41555c2ca9269df0f13e10ec1c35dc. This issue affects the function getJailbreak of the file server/config.py of the compo...

2.9
CVSS
2 months ago
Medium nvd

CVE-2026-85703: A flaw has been found in ramon-victor freegpt-webui up to 098db3dfeb41555c2ca9269df0f13e10ec1c35dc. Affected by this iss

A flaw has been found in ramon-victor freegpt-webui up to 098db3dfeb41555c2ca9269df0f13e10ec1c35dc. Affected by this issue is the function getJailbreak of the file server/backend.py of the component J...

5.5
CVSS
2 months ago
High github

CodeWhale: rlm_eval auto-approves arbitrary Python execution, bypassing the user's approval policy (RCE)

### Maintainer resolution The CodeWhale maintainers validated this report. The affected package ranges are recorded in the advisory metadata. Version 0.8.64 contains the fix in commit 57f3c89471e27ac...

Prompt Injection Remote Code Execution prompt injection deepseek llm
7.8
CVSS
2 months ago
High github

CodeWhale: Argument Injection in `git_blame` Tool Allows Arbitrary File Read Without Approval

### Maintainer resolution The CodeWhale maintainers validated this report. The affected package ranges are recorded in the advisory metadata. Version 0.8.64 contains the fix in commit 9a34b5034d29f05...

Prompt Injection prompt injection deepseek
7.4
CVSS
2 months ago
High github

CodeWhale: Argument Injection in `git_show` Tool Allows Arbitrary File Write Without Approval

### Maintainer resolution The CodeWhale maintainers validated this report. The affected package ranges are recorded in the advisory metadata. Version 0.8.64 contains the fix in commit 9a34b5034d29f05...

9.3
CVSS
2 months ago
High github

CodeWhale: exec_shell_interact sends LLM-controlled input to a running shell without an approval prompt (privilege escalation)

### Maintainer resolution The CodeWhale maintainers validated this report. The affected package ranges are recorded in the advisory metadata. Version 0.8.64 contains the fix in commit 57f3c89471e27ac...

Prompt Injection Auth Bypass prompt injection deepseek llm
7.0
CVSS
2 months ago
Critical nvd

CVE-2026-85694: LaVague 0.2.35 contains a remote code execution vulnerability in PythonFromMarkdownExtractor.extract_as_object that eval

LaVague 0.2.35 contains a remote code execution vulnerability in PythonFromMarkdownExtractor.extract_as_object that evaluates untrusted language model output derived from web page content. Attackers c...

Prompt Injection Remote Code Execution prompt injection indirect prompt
9.2
CVSS
2 months ago
High nvd

CVE-2026-85675: OWL's DocumentProcessingToolkit contains a server-side request forgery vulnerability in the extract_document_content too

OWL's DocumentProcessingToolkit contains a server-side request forgery vulnerability in the extract_document_content tool that fetches caller-supplied URLs with no scheme, host, or IP filtering. Attac...

Prompt Injection SSRF prompt injection
8.7
CVSS
2 months ago
Medium github

CKAN MCP Server: Cache-key canonicalization collision enables cache confusion / poisoning

## Summary The response cache derives its key from an ambiguous string serialization of the request parameters. `canonicalizeParams` joins sorted `${key}=${value}` pairs with `&` and does not escape...

Prompt Injection Agentic / MCP prompt injection indirect prompt mcp server
6.5
CVSS
2 months ago
Medium github

CKAN MCP Server: MQA server allowlist bypass via unanchored regex (`isValidMqaServer`)

## Summary The `ckan_get_mqa_quality` and `ckan_get_mqa_quality_details` tools restrict their `server_url` argument to `dati.gov.it` via a regular expression. The regex is anchored only at the start...

Prompt Injection SSRF Agentic / MCP indirect prompt mcp server agentic
5.3
CVSS
2 months ago
High nvd

CVE-2026-79745: MCPHub is a unified hub for centrally managing and dynamically orchestrating multiple MCP servers/APIs into separate end

MCPHub is a unified hub for centrally managing and dynamically orchestrating multiple MCP servers/APIs into separate endpoints with flexible routing strategies. Prior to version 1.0.32, the built-in p...

Prompt Injection Agentic / MCP prompt injection mcp server llm
7.1
CVSS
2 months ago
High nvd

CVE-2026-82217: In Eclipse Theia versions 1.73.0 up to but not including 1.75.0, the AI "Agent Mode" file-change tools (writeFileContent

In Eclipse Theia versions 1.73.0 up to but not including 1.75.0, the AI "Agent Mode" file-change tools (writeFileContent, suggestFileContent, and the replacement and state helpers) resolved a model-su...

Prompt Injection prompt injection indirect prompt
8.8
CVSS
2 months ago
Medium nvd

CVE-2026-82233: SiYuan before v3.8.1 contains a path traversal vulnerability in the asset.upload MCP tool that accepts arbitrary absolut

SiYuan before v3.8.1 contains a path traversal vulnerability in the asset.upload MCP tool that accepts arbitrary absolute file paths without workspace boundary validation. Attackers can induce the AI...

Prompt Injection Agentic / MCP prompt injection ai agent
6.9
CVSS
2 months ago
Unknown nvd

CVE-2026-37003: Agno up to and including 2.5.8 is vulnerable to Remote Code Execution (RCE) via prompt injection. The PythonTools and Sh

Agno up to and including 2.5.8 is vulnerable to Remote Code Execution (RCE) via prompt injection. The PythonTools and ShellTools components pass unsanitized, LLM-generated arguments directly to execut...

2 months ago
Unknown rss_thehackernews

Amazon Kiro Prompt Injection Can Exfiltrate Sensitive Data Through Kiro Powers

Cybersecurity researchers have disclosed details of a vulnerability in Amazon Kiro, an artificial intelligence (AI)-powered, agentic integrated development environment (IDE), that could facilitate dat...

Prompt Injection Agentic / MCP prompt injection agentic
2 months ago
High nvd

CVE-2026-55557: browse-mcp is a Playwright-based headless-browser MCP server for MCP-capable agents. Prior to 0.8.2, browser_download wr

browse-mcp is a Playwright-based headless-browser MCP server for MCP-capable agents. Prior to 0.8.2, browser_download writes a fetched response body to join(save_dir, filename) without validating the...

Prompt Injection Agentic / MCP prompt injection indirect prompt mcp server
8.6
CVSS
2 months ago
High github

browse-mcp has an arbitrary file write via unconfined download and state paths

### Impact `browser_download` wrote a fetched file to `join(save_dir, filename)` with no validation of `save_dir`, and `browser_save_state` / `browser_load_state` honored an explicit `path` unchanged....

Prompt Injection Agentic / MCP prompt injection indirect prompt
0.0
CVSS
2 months ago