Command injection

Auto-GPT is an experimental open-source application showcasing the capabilities of the GPT-4 language model. The Auto-GPT command line UI makes heavy use of color-coded print statements to signify different types of system messages to the user, including messages that are crucial for the user to...

Path traversal

Auto-GPT is an experimental open-source application showcasing the capabilities of the GPT-4 language model. When Auto-GPT is executed directly on the host system via the provided run.sh or run.bat files, custom Python code execution is sandboxed using a temporary dedicated docker container which...

Design/Logic Flaw

Auto-GPT is an experimental open-source application showcasing the capabilities of the GPT-4 language model. Running Auto-GPT version prior to 0.4.3 by cloning the git repo and executing docker compose run auto-gpt in the repo root uses a different docker-compose.yml file from the one suggested i...

CVE-2023-37275

CVE-2023-37275 affects Auto-GPT prior to v0.4.3, where a malicious external resource could cause the LLM to regurgitate JSON-encoded ANSI escape sequences, which are decoded and printed to the console as part of the model’s thinking process, spoofing system logs. The vulnerability is fixed in rel...

CVE-2023-37275 System logs spoofable in Auto-GPT via ANSI control sequences

Auto-GPT is an experimental open-source application showcasing the capabilities of the GPT-4 language model. The Auto-GPT command line UI makes heavy use of color-coded print statements to signify different types of system messages to the user, including messages that are crucial for the user to...

CVE-2023-37275 System logs spoofable in Auto-GPT via ANSI control sequences

Auto-GPT is an experimental open-source application showcasing the capabilities of the GPT-4 language model. The Auto-GPT command line UI makes heavy use of color-coded print statements to signify different types of system messages to the user, including messages that are crucial for the user to...

CVE-2023-37275 System logs spoofable in Auto-GPT via ANSI control sequences

Auto-GPT is an experimental open-source application showcasing the capabilities of the GPT-4 language model. The Auto-GPT command line UI makes heavy use of color-coded print statements to signify different types of system messages to the user, including messages that are crucial for the user to...

CVE-2023-37274 Python code execution sandbox escape in non-docker version in Auto-GPT

Auto-GPT is an experimental open-source application showcasing the capabilities of the GPT-4 language model. When Auto-GPT is executed directly on the host system via the provided run.sh or run.bat files, custom Python code execution is sandboxed using a temporary dedicated docker container which...

CVE-2023-37274 Python code execution sandbox escape in non-docker version in Auto-GPT

Auto-GPT is an experimental open-source application showcasing the capabilities of the GPT-4 language model. When Auto-GPT is executed directly on the host system via the provided run.sh or run.bat files, custom Python code execution is sandboxed using a temporary dedicated docker container which...

CVE-2023-37274 Python code execution sandbox escape in non-docker version in Auto-GPT

Auto-GPT is an experimental open-source application showcasing the capabilities of the GPT-4 language model. When Auto-GPT is executed directly on the host system via the provided run.sh or run.bat files, custom Python code execution is sandboxed using a temporary dedicated docker container which...

CVE-2023-37274

CVE-2023-37274 affects Auto-GPT prior to 0.4.3. The bug arises in execute_python_code where the basename argument is not sanitized before writing LLM-supplied code to a file, enabling path traversal to overwrite .py files outside the Auto-GPT workspace (e.g., ../../../main.py). This can lead to a...

CVE-2023-37273 Docker escape in Auto-GPT when running from docker-compose.yml included in git repo

Auto-GPT is an experimental open-source application showcasing the capabilities of the GPT-4 language model. Running Auto-GPT version prior to 0.4.3 by cloning the git repo and executing docker compose run auto-gpt in the repo root uses a different docker-compose.yml file from the one suggested i...

CVE-2023-37273 Docker escape in Auto-GPT when running from docker-compose.yml included in git repo

Auto-GPT is an experimental open-source application showcasing the capabilities of the GPT-4 language model. Running Auto-GPT version prior to 0.4.3 by cloning the git repo and executing docker compose run auto-gpt in the repo root uses a different docker-compose.yml file from the one suggested i...

CVE-2023-37273 Docker escape in Auto-GPT when running from docker-compose.yml included in git repo

Auto-GPT is an experimental open-source application showcasing the capabilities of the GPT-4 language model. Running Auto-GPT version prior to 0.4.3 by cloning the git repo and executing docker compose run auto-gpt in the repo root uses a different docker-compose.yml file from the one suggested i...

CVE-2023-37273

CVE-2023-37273 affects Auto-GPT prior to 0.4.3. The root cause is a docker-compose.yml in the repo root mounted into the container without write protection, allowing malicious Python code via execute_python_file/execute_python_code to overwrite the file and abuse it to gain control of the host on...

Auto-GPT 代码注入漏洞

Auto-GPT is an artificial intelligence software agent program open-sourced by Significant Gravitas. A code injection vulnerability exists in versions of Auto-GPT prior to 0.4.3, which stems from the ability to achieve arbitrary code execution on a host running Auto-GPT by overwriting...

PT-2023-25877 · Autogpt · Autogpt

Name of the Vulnerable Software and Affected Versions: Auto-GPT versions prior to 0.4.3 Description: The issue allows for a path traversal attack, enabling the overwrite of any .py file outside the workspace directory by specifying a malicious basename argument, such as ../../../main.py. This can...

Auto-GPT 安全漏洞

Auto-GPT is an artificial intelligence software agent program open-sourced by Significant Gravitas. A security vulnerability exists in versions prior to Auto-GPT 0.4.3, which stems from the possibility that a malicious external resource could cause a misleading message to be printed to the consol...

PT-2023-25876 · Autogpt · Autogpt

Name of the Vulnerable Software and Affected Versions: Auto-GPT versions prior to 0.4.3 Description: The issue arises from the use of a different docker-compose.yml file when running Auto-GPT by cloning the git repo and executing docker compose run auto-gpt in the repo root. This file mounts itse...

a-bot (0.0.1), a-gpt (>=0.1.0, <=0.4.0) +24321 more potentially affected by unknown CVE via atty (>=0.1.2, <=0.2.14)

atty CARGO version =0.1.2, =0.1.0, =0.0.5, =0.2.0, =0.0.1, =0.0.2, =0.4.1, =0.9.0, =0.1.0, =0.2.1, =1.0.3, =0.1.0, =0.1.1 and more Source cves: unknown CVE Source advisory: OSV:GHSA-G98V-HV3F-HCFR...