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.
{
"cna_assigner": "GitHub_M",
"osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/48xxx/CVE-2026-48116.json",
"cwe_ids": [
"CWE-77",
"CWE-88"
]
}{
"cpe": "cpe:2.3:a:mintplexlabs:anythingllm:*:*:*:*:*:*:*:*",
"extracted_events": [
{
"introduced": "0"
},
{
"fixed": "1.13.0"
}
],
"source": [
"CPE_RANGE",
"REFERENCES"
]
}