Prompt Injection
231 entries
Every Prompt Injection entry VulnWatch has indexed, sorted by publication date.
Subscribe to this tag's RSS feed
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...
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...
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...
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...
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...
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...
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...
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
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...
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...
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...
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...
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...
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...
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 `...
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...
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...
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...
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...
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...
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.
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...
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...
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_...
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...