A vulnerability in significant-gravitas/autogpt version 0.5.1 allows an attacker to bypass the shell commands denylist settings. The issue arises when the denylist is configured to block specific commands, such as 'whoami' and '/bin/whoami'. An attacker can circumvent this restriction by executing commands with a modified path, such as '/bin/./whoami', which is not recognized by the denylist.
The product constructs all or part of an OS command using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify the intended OS command when it is sent to a downstream component.
Link | Tags |
---|---|
https://huntr.com/bounties/8a742c13-bb5e-4bc9-8b86-049d8a386050 | third party advisory exploit |
https://github.com/significant-gravitas/autogpt/commit/ef691359b774a1f9f80cf4f5ace9821967b718ed | patch |