Description
AnythingLLM is an application that turns pieces of content into context that any LLM can use as references during chatting. Prior to 1.13.0, the filesystem-search-files agent skill passes its LLM-controlled pattern parameter to ripgrep as a positional argument without a -- end-of-options separator. ripgrep parses any argument that starts with - as an option, so a pattern of --pre=/bin/sh turns ripgrep into a script executor: it runs /bin/sh <file> for every file it walks. An attacker who can chat with an agent on a deployment with the filesystem plugin enabled (the default in the official Docker image) can use this, together with the sibling filesystem-write-text-file skill, to run arbitrary commands inside the AnythingLLM server container. This vulnerability is fixed in 1.13.0.
Problem types
CWE-77: Improper Neutralization of Special Elements used in a Command ('Command Injection')
CWE-88: Improper Neutralization of Argument Delimiters in a Command ('Argument Injection')
Product status
References
github.com/...ng-llm/security/advisories/GHSA-6hrp-7mw6-8v59
github.com/...ng-llm/security/advisories/GHSA-6hrp-7mw6-8v59
github.com/...ommit/94ed62d320df1a06c229e4bc3ee09c2cb5111b33