Description (CNA)
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.
Affected (CNA)
| Vendor / product | Versions |
|---|---|
| Mintplex-Labs / anything-llm | affected < 1.13.0 |
CWE
CWE-77, CWE-88
References
- https://github.com/Mintplex-Labs/anything-llm/security/advisories/GHSA-6hrp-7mw6-8v59
- https://github.com/Mintplex-Labs/anything-llm/commit/94ed62d320df1a06c229e4bc3ee09c2cb5111b33
ADP enrichment
No English description supplied.