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

Kubeshark: MCP `download_file` writes fetched bytes to an unvalidated destination path

**Ecosystem / package:** Go — `github.com/kubeshark/kubeshark` (the `kubeshark` CLI, `kubeshark mcp` subcommand) **Affected component:** `cmd/mcpRunner.go`, MCP tool `download_file` **Affected version...

Prompt Injection Remote Code Execution Agentic / MCP prompt injection indirect prompt mcp server ai agent
5.3
CVSS
18 hours ago
High github

Kubeshark: MCP `start_kubeshark` argument injection via `pod_regex` → image redirect → cluster takeover

**Ecosystem / package:** Go — `github.com/kubeshark/kubeshark` (the `kubeshark` CLI, `kubeshark mcp` subcommand) **Affected component:** `cmd/mcpRunner.go`, MCP tool `start_kubeshark` **Affected versi...

Prompt Injection Agentic / MCP model context protocol prompt injection indirect prompt mcp server
7.2
CVSS
18 hours ago
Medium nvd

CVE-2026-126681: Improper restriction of intended endpoints in the connection configuration handling of the AWS Labs Timestream for Influ

Improper restriction of intended endpoints in the connection configuration handling of the AWS Labs Timestream for InfluxDB MCP Server (awslabs.timestream-for-influxdb-mcp-server) before 0.0.19 might...

Prompt Injection Agentic / MCP prompt injection mcp server
6.8
CVSS
19 hours ago
Critical nvd

CVE-2026-123965: A prompt injection vulnerability in all versions of Jet Admin Cloud Platform allows a remote attacker with a free accoun

A prompt injection vulnerability in all versions of Jet Admin Cloud Platform allows a remote attacker with a free account to expose sensitive .env configuration files and exfiltrate critical credentia...

Prompt Injection prompt injection
9.3
CVSS
3 days ago
Medium nvd

CVE-2026-126767: OpsTree REMS through 1.0.0 contains a prompt injection vulnerability that allows authenticated users to disclose the hid

OpsTree REMS through 1.0.0 contains a prompt injection vulnerability that allows authenticated users to disclose the hidden system prompt by submitting crafted chat input to POST /api/v1/rca/chat. Att...

Prompt Injection prompt injection
5.3
CVSS
5 days ago
Low osv

AG2: Newline injection in SandboxShellTool bypasses allowed=[...] and readonly=True, enabling arbitrary command execution

### Summary SandboxShellTool's restricted modes — allowed=[...] (explicit command allowlist) and readonly=True (implicit READONLY_COMMANDS allowlist) — can both be bypassed by embedding a newline char...

3.1
CVSS
1 week ago
Low nvd

CVE-2026-123498: Vikunja veans before 2.7.1 contains a prompt injection vulnerability that allows project members with write access to in

Vikunja veans before 2.7.1 contains a prompt injection vulnerability that allows project members with write access to inject instructions by setting project titles or task content rendered verbatim in...

Prompt Injection prompt injection
2.1
CVSS
1 week ago
Medium nvd

CVE-2026-123851: In JetBrains Junie GitHub Action before 1.6.4 prompt injection protection could be bypassed via HTML-encoded characters

In JetBrains Junie GitHub Action before 1.6.4 prompt injection protection could be bypassed via HTML-encoded characters

Prompt Injection prompt injection
5.4
CVSS
1 week ago
Unknown rss_thehackernews

Researchers Bypass ChatGPT Lockdown Mode to Exfiltrate Chats Without User Interaction

Cybersecurity researchers have disclosed details of a now-patched vulnerability that could be exploited to bypass Lockdown Mode protections in OpenAI ChatGPT. Lockdown Mode was introduced by the arti...

Prompt Injection prompt injection chatgpt openai
1 week ago
Medium nvd

CVE-2026-122235: Jan from 0.8.5 before 0.8.8 contains a workspace guard bypass vulnerability in the agent-tools gate.rs that allows attac

Jan from 0.8.5 before 0.8.8 contains a workspace guard bypass vulnerability in the agent-tools gate.rs that allows attackers to write files outside the workspace via dangling symlinks. Attackers suppl...

Prompt Injection prompt injection
5.7
CVSS
1 week ago
Unknown rss_thehackernews

Researchers Uncover Prompt Adware Hidden in OpenAI Codex Jailbreak Toolkit

Cybersecurity researchers have disclosed details of an OpenAI Codex jailbreak bundle that's designed to modify an artificial intelligence (AI) agent's trusted instructions to insert advertisements for...

Prompt Injection jailbreak openai
1 week ago
Medium github

DBHub: MySQL and MariaDB comment interpretation bypasses read-only SQL validation

The read-only mode can be bypassed on the MySQL and MariaDB connectors. In read-only mode a caller can still execute arbitrary write and DDL statements (for example DROP TABLE), which defeats the prot...

Prompt Injection Agentic / MCP prompt injection ai agent
0.0
CVSS
2 weeks ago
Medium nvd

CVE-2026-61789: DBHub is a database MCP server for Postgres, MySQL, SQL Server, Oracle, MariaDB, SQLite. Prior to 0.22.6, read-only SQL

DBHub is a database MCP server for Postgres, MySQL, SQL Server, Oracle, MariaDB, SQLite. Prior to 0.22.6, read-only SQL validation can be bypassed on the MySQL and MariaDB connectors. In `src/utils/sq...

Prompt Injection Agentic / MCP prompt injection mcp server
6.1
CVSS
2 weeks ago
Critical nvd

CVE-2026-119050: Agno through 3.1.11 contains an unsafe reflection vulnerability in PandasTools that allows attackers to invoke arbitrary

Agno through 3.1.11 contains an unsafe reflection vulnerability in PandasTools that allows attackers to invoke arbitrary pandas functions by supplying model-controlled function names to getattr(). Att...

Prompt Injection prompt injection
9.2
CVSS
2 weeks ago
High nvd

CVE-2026-59176: Functype is a family of TypeScript functional programming libraries. Prior to 1.4.4, the `set_functype_version` MCP tool

Functype is a family of TypeScript functional programming libraries. Prior to 1.4.4, the `set_functype_version` MCP tool in `functype-mcp-server` accepts an unconstrained `version` string using only `...

Prompt Injection Agentic / MCP prompt injection indirect prompt mcp server
7.8
CVSS
2 weeks ago
High github

Strands Agents: Local Privilege Escalation via Symlink Attack in Default Session File Storage

## Summary The `FileSessionManager` defaults to storing session data in `/tmp/strands/sessions/` (a world-writable directory) using predictable file paths and a write pattern (`open(path + ".tmp", "w...

7.1
CVSS
3 weeks ago
High nvd

CVE-2026-117567: esp-mcp through commit 28afddf contains an OS command injection vulnerability that allows attackers to run arbitrary com

esp-mcp through commit 28afddf contains an OS command injection vulnerability that allows attackers to run arbitrary commands by supplying shell metacharacters in MCP tool parameters. Attackers influe...

8.5
CVSS
3 weeks ago
High nvd

CVE-2026-114107: HKUDS Vibe-Trading from 0.1.0 before 0.1.7 contains an indirect prompt injection vulnerability that allows remote attack

HKUDS Vibe-Trading from 0.1.0 before 0.1.7 contains an indirect prompt injection vulnerability that allows remote attackers to execute shell commands as root by planting instructions in documents or w...

Prompt Injection SSRF prompt injection indirect prompt
8.7
CVSS
3 weeks ago
High nvd

CVE-2026-109440: LangAlpha through 2026.09.07 contains an indirect prompt injection vulnerability that allows remote attackers to execute

LangAlpha through 2026.09.07 contains an indirect prompt injection vulnerability that allows remote attackers to execute shell commands or Python by planting instructions in web content retrieved by t...

Prompt Injection prompt injection indirect prompt
8.6
CVSS
4 weeks ago
High nvd

CVE-2026-112308: crewai-tools through 1.15.28 contains a server-side request forgery vulnerability in SeleniumScrapingTool that allows at

crewai-tools through 1.15.28 contains a server-side request forgery vulnerability in SeleniumScrapingTool that allows attackers to fetch internal resources because it never applies the validate_url pr...

Prompt Injection SSRF prompt injection crewai
8.3
CVSS
4 weeks ago
Unknown nvd

CVE-2026-95183: An issue in the context-compaction feature of DeepSeek Harness (dsh) commit c291e796 allows attackers to execute a promp

An issue in the context-compaction feature of DeepSeek Harness (dsh) commit c291e796 allows attackers to execute a prompt injection attack via crafted external content.

Prompt Injection prompt injection deepseek
1 month ago
High github

Nginx UI: MCP nginx_config_add skips config directive validation → authenticated nginx directive injection (RCE on the official image)

## Summary `internal/config/validation.go` (`ValidateConfigFile`) is a security control that blocks dangerous nginx directives — `js_*`, `perl_*`, `load_module` of the njs/perl modules, and `user root...

8.8
CVSS
1 month ago
High nvd

CVE-2026-76066: IntentKit through 2.6.3 contains an authorization bypass vulnerability where the executor validates tool calls against t

IntentKit through 2.6.3 contains an authorization bypass vulnerability where the executor validates tool calls against the full tool registry rather than the per-request narrowed tool advertisement en...

Prompt Injection Auth Bypass prompt injection indirect prompt
8.7
CVSS
1 month ago
High nvd

CVE-2026-84317: Nginx UI is a web user interface for the Nginx web server. Prior to 2.4.1, internal/config/validation.go (ValidateConfig

Nginx UI is a web user interface for the Nginx web server. Prior to 2.4.1, internal/config/validation.go (ValidateConfigFile) is a security control that blocks dangerous nginx directives — js_*, perl_...

Prompt Injection prompt injection
8.8
CVSS
1 month ago
Medium nvd

CVE-2026-108756: Abilityai Trinity through 0.9.5 contains a missing authorization vulnerability in the Telegram router that allows agent-

Abilityai Trinity through 0.9.5 contains a missing authorization vulnerability in the Telegram router that allows agent-scoped MCP API keys to perform human-only binding operations. Attackers controll...

Prompt Injection prompt injection
5.3
CVSS
1 month ago