| CVE |
Vendors |
Products |
Updated |
CVSS v3.1 |
| 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 from 0.1.0 before 0.1.7 contains a path traversal vulnerability that allows remote attackers to read sensitive server files through LLM agent file-read tools. Attackers can prompt the agent to invoke read_document, which lacks sandbox checks, or safe_user_path-gated tools to leak /etc/shadow, /proc/self/environ API keys, and /root credentials. |
| HKUDS Vibe-Trading from 0.1.0 before 0.1.7 contains a missing authentication vulnerability that allows unauthenticated attackers to access the FastAPI surface because require_auth() returns early when API_AUTH_KEY is unset. Attackers can post messages to /sessions/{id}/messages to trigger root shell commands via BashTool, upload .py or .sh files via /upload, read session histories, and obtain partial API keys. |
| DeepTutor 1.4.0 contains an authorization bypass vulnerability in the book confirmation flow. An unauthenticated or unauthorized caller can reuse a publicly exposed book_id to submit a confirm-proposal request for an existing book, causing unauthorized overwrites of persisted metadata and spine content. |
| deeptutor 1.4.0 contains a path traversal issue in EditFileTool.execute. Through the live tutorbot WebSocket interface, a remote caller can induce the tool layer to write or edit absolute paths outside the intended bot workspace. |
| deeptutor 1.4.0 contains an authorization bypass through a user-controlled object identifier in TurnRuntimeManager.regenerate_last_turn. A remote caller can enumerate or obtain a session_id and trigger regenerate on another user's session. |
| deeptutor 1.4.0 contains code injection in ExecTool.execute. Through the live tutorbot WebSocket interface, a remote caller can induce the tool layer to execute reviewer-chosen shell commands in the service environment. |
| deeptutor 1.4.0 contains an authorization bypass through a user-controlled object identifier in TutorBotManager.write_bot_file. A remote caller can enumerate bot IDs and overwrite another bot's whitelisted control files through the HTTP tutorbot file route. |
| 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. |
| 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, 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. |
| LightRAG provides simple and fast retrieval-augmented generation. Prior to 1.5.5, lightrag_webui/src/components/retrieval/ChatMessage.tsx renders answer and thinking content with react-markdown, rehypeRaw, and skipHtml=false without an HTML sanitizer. An attacker who can add a document can store raw HTML that is returned through the query path and rendered as active content by MessageMarkdown. A user who later retrieves the content can execute attacker-controlled JavaScript through elements such as an iframe srcdoc; the additional Mermaid securityLevel: loose rendering path also injects generated SVG through innerHTML. The script runs in the LightRAG WebUI origin and can read the API token in localStorage and perform API actions as the victim. This issue is fixed in version 1.5.5. |
| LightRAG provides simple and fast retrieval-augmented generation. Prior to 1.5.5, the LightRAG API server returns raw Python exception text from error handlers in document_routes.py, graph_routes.py, query_routes.py, ollama_api.py, and lightrag_server.py. The detail=str(e), detail=str(exc), and equivalent formatted-message paths expose server filesystem paths, database host, port, user, and database names, language-model provider diagnostics, configuration details, and Python library internals to a network client that can trigger an error. The default unauthenticated configuration makes those responses reachable without credentials, and URI-configured backends can disclose connection strings containing credentials depending on the underlying driver error. 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. |
| 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 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 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 security vulnerability has been detected 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 Shell Allowlist Handler. Such manipulation leads to os command injection. The attack can be executed remotely. The exploit has been disclosed publicly and may be used. Upgrading to version 0.3.0 is recommended to address this issue. The name of the patch is 4562. It is advisable to upgrade the affected component. Multiple issues were reported to the project. They reacted with a high level of professionalism and kindness: "These five reports are variants of the same root cause: validation of shell commands containing multiple segments, wrappers, comments, or chained commands. The issue was fixed by validating every executable shell segment against the configured allowlist". |
| 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". |
| 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. |
