HKUDS Vibe-Trading versions from 0.1.0 up to but not including 0.1.7 have a missing authentication vulnerability. This flaw allows unauthenticated attackers to access critical API endpoints because the require_auth() function returns early if the API_AUTH_KEY is not set. Exploitation enables attackers to execute root shell commands, upload malicious scripts, read session histories, and obtain partial API keys. The vulnerability has a CVSS 4.0 score of 9.3, indicating critical severity.
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 web pages the agent processes. BashTool and BackgroundRunTool pass model-emitted commands to subprocess.run with shell=True and no allow-list or approval step, and read_url fetches arbitrary URLs, enabling command execution and server-side request forgery.
HKUDS Vibe-Trading versions from 0.1.0 up to but not including 0.1.7 contain a path traversal vulnerability. This flaw allows remote attackers to read sensitive server files by exploiting LLM agent file-read tools that lack proper sandboxing. Attackers can use the read_document function or safe_user_path-gated tools to access critical files such as /etc/shadow, /proc/self/environ, and /root credentials. The vulnerability has a high severity with a CVSS score of 8.7.
A vulnerability was identified in HKUDS AnyTool 0.1.0. Affected is the function subprocess.run of the file anytool/local_server/main.py of the component Execute Endpoint. The manipulation of the argument command/shell leads to os command injection. It is possible to initiate the attack remotely. The exploit is publicly available and might be used. The project was informed of the problem early through an issue report but has not responded yet.
CVE-2026-86062 is a cross-site scripting (XSS) vulnerability in HKUDS LightRAG versions prior to 1.5.5. The vulnerability arises because the application renders user-supplied content with react-markdown and rehypeRaw without sanitizing HTML, allowing attackers to inject malicious scripts. This can lead to execution of attacker-controlled JavaScript in the context of the LightRAG WebUI, potentially exposing API tokens stored in localStorage and enabling unauthorized API actions. The issue is fixed in version 1.5.5.
LightRAG provides simple and fast retrieval-augmented generation. Prior to 1.5.5, _validated_addresses in lightrag/parser/markdown/parser.py evaluates the literal resolved address with ipaddress.is_global without consistently classifying an IPv4 address embedded in an IPv6 transition wrapper. A caller who can upload a Markdown or textpack document can supply an external image URL using NAT64 64:ff9b::/96 or an IPv4-compatible form that embeds a loopback, private, or cloud-metadata IPv4 address. On a deployment with compatible NAT64 or DNS64 routing, _download and _build_guarded_opener accept the wrapper and fetch the internal resource, whose body is then ingested. Current interpreter behavior already blocks some RFC 8215 and 6to4 forms, but the fixed guard handles all documented wrappers without becoming more permissive than the standard library. This issue is fixed in version 1.5.5.
LightRAG provides simple and fast retrieval-augmented generation. Prior to 1.5.5, the POST /login endpoint in lightrag/api/lightrag_server.py does not impose a rate limit, account lockout, delay, or counter for failed authentication attempts. A network attacker can submit password guesses at full request speed until a valid account password is found. Successful credential recovery grants authenticated access to documents, the knowledge graph, and administrative operations. This issue is fixed in version 1.5.5.
LightRAG provides simple and fast retrieval-augmented generation. Prior to 1.5.5, verify_password in lightrag/api/passwords.py compares plaintext AUTH_ACCOUNTS password values with Python's == operator. The comparison can return after the first mismatching byte, creating response-time differences based on password length and matching prefixes. A network attacker with sufficiently low-latency access can repeatedly query the /login endpoint and use the timing oracle to recover a plaintext-configured password character by character. Deployments using bcrypt-prefixed password values are not affected by this comparison path. This issue is fixed in version 1.5.5.
CVE-2026-85709 is a vulnerability in HKUDS LightRAG prior to version 1.5.5 where error messages returned by the API server expose sensitive information. These error messages include raw Python exception text revealing server filesystem paths, database connection details including host, port, user, and database names, language model provider diagnostics, configuration details, and Python library internals. The default unauthenticated configuration allows these detailed error responses to be accessed without credentials, potentially exposing connection strings with credentials depending on the backend driver error. This issue is fixed in version 1.5.5.
HKUDS nanobot versions before 0.3.0 have a server-side request forgery (SSRF) vulnerability in the WebFetchTool component. The vulnerability arises because the _validate_url() function does not block internal IP ranges and private addresses. This allows attackers to instruct the bot to fetch internal resources such as cloud metadata endpoints, localhost services, and RFC 1918 addresses, potentially exposing IAM credentials and internal service data.
A vulnerability was identified in HKUDS nanobot up to 0.2.1. The affected element is the function ExecTool._guard_command/ExecTool._spawn of the file nanobot/agent/tools/shell.py of the component ExecTool. Such manipulation leads to argument injection. It is possible to launch the attack remotely. The name of the patch is af582246f141311d574551b7571a517bcc3df750. It is best practice to apply a patch to resolve this issue.
A vulnerability was determined in HKUDS nanobot up to 0.2.1. Impacted is the function ExecTool._guard_command/ExecTool._spawn of the file nanobot/agent/tools/shell.py of the component ExecTool. This manipulation causes incomplete blacklist. It is possible to initiate the attack remotely. Patch name: af582246f141311d574551b7571a517bcc3df750. Applying a patch is the recommended action to fix this issue.
AutoAgent contains an unauthenticated remote code execution vulnerability in the TCP server that binds to all interfaces and executes attacker-supplied commands as root. Attackers can connect to the exposed communication port and execute arbitrary bash commands within the container, gaining access to bind-mounted host workspace directories.
A vulnerability has been found in HKUDS AI-Trader up to d03ff6c056b32ced735adf7c19ed8175adb1c8df. The affected element is an unknown function of the file service/server/routes_agent.py of the component selfRegister API Endpoint. Such manipulation of the argument initial_balance leads to business logic errors. The attack may be launched remotely. This attack is characterized by high complexity. The exploitability is described as difficult. The exploit has been disclosed to the public and may be used. This product operates on a rolling release basis, ensuring continuous delivery. Consequently, there are no version details for either affected or updated releases. profit_percent_for_display() divides by INITIAL_CAPITAL + deposited, and challenge scoring's return_pct also normalises against the attacker-inflated starting_cash. So an inflated initial_balance does not yield artificial percent returns - it inflates the absolute cash/equity column only, which is a cosmetic/leaderboard-gaming concern in a simulated game.
A vulnerability has been found in HKUDS nanobot up to 0.2.1. This affects the function _download_image_data_url of the file nanobot/providers/image_generation.py of the component Provider-returned Image URL Handler. The manipulation leads to server-side request forgery. It is possible to initiate the attack remotely. The exploit has been disclosed to the public and may be used. The identifier of the patch is 5095. It is recommended to apply a patch to fix this issue. The vendor explains: "We confirm that provider-returned image URLs required the same SSRF protections applied to other network retrieval paths. (...) The patch is currently available on main and is planned for the next patch release, v0.3.1."
A flaw has been found in HKUDS nanobot up to 0.2.1. The impacted element is the function ExecTool._prepare_command of the file nanobot/agent/tools/shell.py of the component Login-shell Environment Handler. Executing a manipulation can lead to information disclosure. The attack requires local access. The exploit has been published and may be used. Upgrading to version 0.3.0 is sufficient to resolve this issue. This patch is called 4525. The affected component should be upgraded. Multiple issues were reported to the project. They reacted with a high level of professionalism and kindness: "The report concerns shell startup files reintroducing environment variables when command execution defaults to a login shell. The default was changed so exec does not use a login shell unless explicitly requested".
A vulnerability was detected in HKUDS nanobot up to 0.2.1. The affected element is the function connect_mcp_servers of the file nanobot/agent/tools/mcp.py of the component MCP enabledTools Scope Handler. Performing a manipulation results in improper access controls. The attack is possible to be carried out remotely. The exploit is now public and may be used. Upgrading to version 0.3.0 is sufficient to fix this issue. The patch is named 4436. You should upgrade the affected component. Multiple issues were reported to the project. They reacted with a high level of professionalism and kindness: "Both reports describe the same root cause: MCP resource and prompt wrappers could be registered outside the intended enabledTools scope. The registration boundary was corrected".
LightRAG provides simple and fast retrieval-augmented generation. Through version 1.5.4, the LightRAG API server binds to all network interfaces with authentication disabled by default, allowing an unauthenticated network attacker to read indexed document content, upload or delete documents, modify the knowledge graph, cancel pipelines, clear caches, and consume LLM resources. This issue is mitigated in version 1.5.5rc1.