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 nvd

CVE-2026-108600: open-multi-agent (@open-multi-agent/core) 1.5.0 through 1.21.2 contains a link following vulnerability in the file_write

open-multi-agent (@open-multi-agent/core) 1.5.0 through 1.21.2 contains a link following vulnerability in the file_write tool sandbox that allows attackers to create files outside the workspace root b...

Prompt Injection prompt injection
5.7
CVSS
1 month ago
Medium nvd

CVE-2026-108599: phi 0.1.1 through 0.28.4 contains an improper link resolution vulnerability that allows malicious repositories to bypass

phi 0.1.1 through 0.28.4 contains an improper link resolution vulnerability that allows malicious repositories to bypass workspace_only_writes by exploiting lexical-only path checks in the permission...

Prompt Injection prompt injection
5.7
CVSS
1 month ago
Medium nvd

CVE-2026-108592: mini-swe-agent 1.10.0 through 2.4.6 contains an information exposure vulnerability in BubblewrapEnvironment because bwra

mini-swe-agent 1.10.0 through 2.4.6 contains an information exposure vulnerability in BubblewrapEnvironment because bwrap omits --clearenv, so sandboxed commands inherit the host environment. Attacker...

Prompt Injection prompt injection
6.0
CVSS
1 month ago
Low nvd

CVE-2026-108583: zotero-mcp 0.10.0 through 0.14.1 contains a server-side request forgery vulnerability that allows attackers to reach int

zotero-mcp 0.10.0 through 0.14.1 contains a server-side request forgery vulnerability that allows attackers to reach internal services because _fetch_embedded_metadata fetches URLs without destination...

Prompt Injection SSRF prompt injection
2.3
CVSS
1 month ago
High github

PraisonAI: Shell command allowlist bypass via find -exec built-in action

### Summary The shell command execution hardening introduced in PraisonAI npm 1.7.2 / Python 4.6.58 to fix GHSA-5jv7-2mjm-h6qj (utility-tools shell chaining) and GHSA-vjv9-7m7j-h833 (SandboxExecutor...

Prompt Injection Agentic / MCP prompt injection llm agent llm
8.8
CVSS
1 month ago
Critical github

PraisonAI: AICoder Arbitrary File Write and Command Execution via LLM Tool Calls

### Summary The `AICoder` UI component exposes `write_to_file` and `execute_command` tools to the LLM with no path validation and no command sanitization. An attacker can achieve arbitrary file write...

9.9
CVSS
1 month ago
Medium github

PraisonAI: Prompt-injection defense blocks only when 3+ detector families fire simultaneously; realistic single-vector injections pass through unblocked

## Summary PraisonAI's opt-in prompt-injection defense (`enable_injection_defense()`) only blocks at `ThreatLevel.CRITICAL`, which requires three or more distinct detector families to match simultane...

Prompt Injection prompt injection
5.3
CVSS
1 month ago
Critical github

PraisonAI: CodeAgent Executes LLM-Generated Code Without Sandboxing and Leaks All Environment Secrets

### Summary `CodeAgent._execute_python()` executes LLM-generated Python code in a subprocess with the complete parent-process environment (`os.environ.copy()`), zero AST validation, zero import restri...

10.0
CVSS
1 month ago
High github

PraisonAI: Prompt Injection Defense Bypassed for HIGH-Level Threats

### Summary Injection Defense is a purpose-built prompt injection defense layer. It scans LLM inputs through six detection categories: instruction overrides, authority claims, boundary manipulation, o...

Prompt Injection prompt injection adversarial llm
7.5
CVSS
1 month ago
High github

PraisonAI: AgentMail webhook lacks signature verification, allowing unauthenticated message injection and sender spoofing

## Summary PraisonAI's AgentMail bot, when run in webhook (or hybrid) mode, starts an aiohttp webhook server bound to `0.0.0.0` and processes inbound `message.received` events **without verifying any...

Prompt Injection prompt injection llm
7.3
CVSS
1 month ago
High github

Langflow: Prompt injection in Langflow Smart Transform can lead to code execution

## Summary Langflow versions 1.3.0 through 1.10.2 contain a code-injection vulnerability in the Smart Transform (`LambdaFilterComponent`) component. Smart Transform places flow-author instructions a...

Prompt Injection prompt injection langflow llm
8.8
CVSS
1 month ago
Medium github

SiYuan MCP asset.upload Reads Arbitrary Absolute File Paths (Workspace Boundary Bypass)

# Security Advisory — SiYuan MCP `asset.upload` Reads Arbitrary Absolute File Paths (Workspace Boundary Bypass) | Field | Value | |---|---| | **Disclosed by** | joysinleung (`[email protected]`)...

Prompt Injection Agentic / MCP prompt injection ai agent
5.7
CVSS
1 month ago
Critical github

Vibe-Trading LLM-callable tools permit command execution, code injection, and SSRF

### Summary: 5 findings — `BashTool` shell-injection sink (F6, the canonical RCE primitive), `BackgroundRunTool` async shell-injection sink (F7), backtest `exec_module()` runs top-level statements be...

10.0
CVSS
1 month ago
High nvd

CVE-2025-71427: Office-PowerPoint-MCP-Server through 2.0.7 contains a path traversal vulnerability that allows MCP callers to write and

Office-PowerPoint-MCP-Server through 2.0.7 contains a path traversal vulnerability that allows MCP callers to write and read files outside the working directory by supplying absolute paths or ../ sequ...

Prompt Injection Agentic / MCP prompt injection ai agent
7.6
CVSS
1 month ago
High nvd

CVE-2026-96561: The AI Engine – The Chatbot, AI Framework & MCP for WordPress plugin for WordPress is vulnerable to Stored Cross-Site Sc

The AI Engine – The Chatbot, AI Framework & MCP for WordPress plugin for WordPress is vulnerable to Stored Cross-Site Scripting in versions up to, and including, 3.8.0 This is due to a chain of missin...

Prompt Injection prompt injection indirect prompt
7.2
CVSS
1 month ago
High nvd

CVE-2026-102697: Ollama versions 0.14.0 before 0.31.2 contain an incorrect authorization vulnerability in the experimental agent mode Bas

Ollama versions 0.14.0 before 0.31.2 contain an incorrect authorization vulnerability in the experimental agent mode Bash tool approval mechanism that fails to properly parse shell syntax. Attackers w...

Prompt Injection prompt injection ollama
8.5
CVSS
1 month ago
Critical nvd

CVE-2026-77177: Open GenAI Stack (aka ogx-ai) 2026-06-11, as used in the Meta AI backend for WhatsApp and other products, allows code ex

Open GenAI Stack (aka ogx-ai) 2026-06-11, as used in the Meta AI backend for WhatsApp and other products, allows code execution because prompt injection (with Jinja2 template syntax) can be used to ac...

Prompt Injection prompt injection genai
9.8
CVSS
1 month ago
Low nvd

CVE-2026-97228: Rapid7 Bulk Export MCP versions 0.2.5 through 0.6.1 suffer from a GraphQL query injection issue in the export-status com

Rapid7 Bulk Export MCP versions 0.2.5 through 0.6.1 suffer from a GraphQL query injection issue in the export-status component (`get_export_status` in `src/export_manager.py`), whereby the `export_id`...

Prompt Injection prompt injection indirect prompt
2.7
CVSS
1 month ago
High github

@bytebase/dbhub's read-only mode does not prevent database writes

### Summary Setting `readonly = true` on the `execute_sql` tool does not make the connection read-only. The connectors are written to set PostgreSQL `default_transaction_read_only=on` (and open SQLi...

7.4
CVSS
1 month ago
Critical github

DBHub HTTP transport DNS rebinding allows unauthenticated browser-origin SQL execution

### Summary DBHub `0.21.2` exposes an unauthenticated HTTP MCP endpoint when started with the documented HTTP transport mode, for example `--transport http --port 8080`. The HTTP server attempts to...

Prompt Injection prompt injection
0.0
CVSS
1 month ago
Critical github

Decepticon: Role-boundary forgery via ChatML special-token literals in web crawl output composed into LLM context

## Summary Decepticon wraps web crawl results — the output of agent reconnaissance against target services — into LLM messages without neutralizing ChatML special-token literals. Under the BYOK (Brin...

Prompt Injection Remote Code Execution prompt injection transformers langchain anthropic jailbreak deepseek mistral ollama sglang openai llama vllm qwen llm
10.0
CVSS
1 month ago
Critical nvd

CVE-2026-61742: DBHub is a database MCP server for Postgres, MySQL, SQL Server, Oracle, MariaDB, SQLite. Versions prior to 0.22.5 expose

DBHub is a database MCP server for Postgres, MySQL, SQL Server, Oracle, MariaDB, SQLite. Versions prior to 0.22.5 expose an unauthenticated HTTP MCP endpoint when started with the documented HTTP tran...

Prompt Injection Agentic / MCP prompt injection mcp server
9.3
CVSS
1 month ago
High github

MCP Atlassian: Arbitrary file read/exfiltration via upload_attachment missing validate_safe_path()

## Summary The `upload_attachment` method in `confluence/attachments.py` reads and uploads arbitrary local files to Confluence without calling `validate_safe_path()`. Both download methods (`download...

Prompt Injection Agentic / MCP prompt injection mcp server ai agent
7.7
CVSS
1 month ago
High github

MCP Atlassian: Arbitrary server-local file upload to Jira/Confluence attachments via unrestricted file_path parameters

## Summary The Jira and Confluence attachment upload tools accept caller-controlled file path parameters and read those paths from the MCP server's local filesystem before uploading the file as an At...

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