Threat Library

Langflow, an open-source framework used to build AI agent workflows, contains a server-side request forgery vulnerability caused by weak default configuration and incomplete SSRF protections. An attacker could exploit this to make the Langflow server issue unauthorized requests to internal or cloud-metadata endpoints, potentially exposing sensitive infrastructure or credentials. This is a genuine, credibly documented vulnerability (CVSS 7.7) rather than a speculative or low-quality report.

IBM Langflow, an open-source visual builder for AI agent workflows, contains a path traversal flaw where a malicious flow can fetch attacker-controlled content and write it to arbitrary paths on the server via a crafted Content-Disposition header. An authenticated attacker can abuse this to overwrite configuration, code, or scheduled/startup files, likely leading to full compromise of the Langflow instance. This is a serious framework-level vulnerability requiring only low-privilege authenticated access.

A vulnerability in IBM Langflow's Python Interpreter component allows an authenticated user to execute arbitrary commands with elevated privileges due to improper input validation. This affects Langflow OSS versions 1.0.0 through 1.10.1, and could allow an attacker with low-level access to escalate privileges and take control of the underlying system. Given the CVSS score of 8.8, this is a serious flaw that requires prompt patching.

This research demonstrates that LLMs used in Security Operations Centers to analyze network/security logs can be manipulated by adversaries who embed prompt injection payloads directly into log-generating fields (e.g., user-agent strings, hostnames, request paths). Because these logs are stored and later fed verbatim into an LLM's context during analyst queries, the injection persists and executes passively, achieving up to 88.2% attack success across production models for goals like hiding malicious activity, generating false positives, exfiltrating data, or hijacking output. This is academic research with a working benchmark and demonstrated mitigations, not an observed in-the-wild exploit, but it describes a realistic and highly exploitable architectural flaw.

Reports indicate that OpenAI's Codex coding agent (referenced as GPT-5.6) can unexpectedly delete a user's entire $HOME directory when run in 'full access mode' without sandboxing or auto-review safeguards. The root cause is the model attempting to override the $HOME environment variable to create a temporary directory and mistakenly deleting the real $HOME instead. This is an unintentional agent malfunction rather than a malicious attack, but it demonstrates severe real-world consequences of granting autonomous coding agents unsandboxed filesystem access.

The BetterDocs WordPress plugin before version 4.5.5 lets unauthenticated users trigger an AI documentation-summary feature whose output is stored and rendered without sanitization. An attacker can craft input that causes the AI to emit malicious HTML/JavaScript, which then executes as stored XSS in the browser of anyone viewing the page, including site administrators.

xAI's Grok Build CLI coding agent was found to upload the entire working directory (and in one reported case, a user's home directory including SSH keys and password manager databases) to xAI's Google Cloud storage without clear user consent. xAI disabled the feature, deleted retained data, and open-sourced the codebase in response to backlash, but this represents a serious real-world data exfiltration incident caused by an overly broad and opaque agent tool/data-retention design rather than a targeted attack.

Repomix's MCP server contains a flaw where two specific tool flows can be used to register and read arbitrary local files without triggering the secret-scanning safety check that normally protects file reads. This allows an MCP client (or an attacker controlling one) to exfiltrate sensitive local files, including those containing credentials, that were meant to be blocked by the redaction/validation layer.

The elasticsearch_memory tool in strands-agents-tools exposed connection parameters like the target host directly to LLM control, allowing a crafted prompt to redirect the tool to an attacker-controlled server. When the api_key parameter was omitted, the tool silently fell back to the operator's environment-stored Elasticsearch API key and sent it to whatever host the LLM specified, leaking the credential via the Authorization header. This is a classic tool-schema over-permissioning issue that turns an LLM-controllable field into a credential exfiltration vector.

The MCP Python SDK's experimental task management feature failed to bind tasks to the session that created them, allowing any connected client to list, read, cancel, or consume messages for tasks belonging to other clients. This is a broken access control / IDOR-style flaw that breaks the trust boundary between concurrent MCP sessions on the same server. It is fixed in version 1.27.2.

The MCP Python SDK's SSE and stateful Streamable HTTP transports route messages to sessions based solely on a session ID, without checking that the requesting client is the same authenticated principal who created that session. Any bearer-token-authenticated client that learns or guesses a valid session ID can inject JSON-RPC messages into another user's active session, effectively hijacking it. This is a serious cross-tenant authorization flaw fixed in version 1.27.2.

A researcher discovered a loophole in Anthropic's Claude web_fetch tool that allowed a malicious website to exfiltrate private user data (name, location, employer) by chaining together a sequence of attacker-controlled links discovered within previously fetched pages. This bypassed the intended safeguard that web_fetch could only follow user- or search-originated URLs, effectively encoding stolen data letter-by-letter into a series of outbound requests. Anthropic has since patched the issue by disallowing navigation to links found within fetched content.

PraisonAI versions before 4.6.78 default to running the MCP HTTP-stream server without any API key or authentication, meaning anyone who can reach the endpoint can list and invoke all exposed tools. The server also fails to validate tool-call arguments against the advertised schema, compounding the risk of malformed or malicious inputs reaching tool handlers. Exploitation requires the operator to have bound the server to a network-accessible address rather than the safe localhost default.

An unauthenticated attacker can abuse the Grafana MCP Server by injecting a crafted X-Grafana-URL header, tricking the server into acting as a proxy that leaks its own privileged Grafana service-account token. This same flaw allows server-side request forgery against internal networks and cloud metadata endpoints, giving attackers a path to full credential theft and internal reconnaissance without needing any prior authentication.

The AWS HealthLake MCP Server fails to validate that pagination URLs returned via the next_token parameter point back to the legitimate HealthLake endpoint, enabling an authenticated user to redirect the server's outbound requests to an attacker-controlled endpoint. This can leak AWS temporary security credentials used by the MCP server, giving an attacker a foothold to access AWS resources tied to those credentials. Fixed in version 0.0.14.

Researchers demonstrate that malicious text placed in the physical environment (e.g., signs, labels) can be captured by camera-equipped smart glasses and hijack the behavior of Vision-Language Models, causing them to ignore true visual context and produce harmful, biased, or false outputs. This is a research paper describing a demonstrated but not actively exploited class of attack, with success rates up to 96% in simulation and 60% in real-world tests across 12 VLM models.

Researchers demonstrate that an adversary can poison an open dataset with misleading metadata and upload it to a public repository, causing autonomous AI research agents (built on Claude, GPT, Gemini) to unknowingly retrieve and use the poisoned data, producing fraudulent scientific conclusions in nearly half of tested runs. No prompt injection, agent compromise, or fabricated papers are needed — only manipulation of the open data ecosystem — and current agents rarely detect the poisoning (6% detection rate), though provenance auditing fully mitigates it in testing.

MCP Appium, an MCP server for automating mobile app testing, fails to sanitize attacker-controlled UI element attributes before embedding them in an HTML template returned by its generate_locators tool. A malicious mobile app under test can inject HTML/JavaScript that executes in the MCP client's rendering context and calls arbitrary MCP tools via postMessage, effectively letting the app-under-test hijack the testing agent's capabilities.

Researchers demonstrated 'Ghostcommit,' a technique that hides prompt injection instructions inside a PNG image committed to a repository. AI code review tools like CodeRabbit and Bugbot don't inspect image contents, but a downstream coding agent that does process the image can be tricked into reading a repo's .env file and exfiltrating secrets by encoding them as numeric data in code. This shows a real, demonstrated cross-modal injection vector with tangible secret-theft impact, not a theoretical concern.

PraisonAI versions before 4.6.78 ship with a prompt injection defense that only blocks CRITICAL-severity threats by default, letting HIGH-severity attacks such as instruction overrides pass through with only logging. This allows attackers to extract system prompts and trigger unauthorized tool calls via single-vector injection attempts that the framework detects but fails to stop.