AnythingLLM: RCE via ripgrep --pre argument injection in filesystem-search-files agent skill
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 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.
- Products
- Not specified
- Affected versions
- Not specified
- Fixed versions
- Not specified
- CVEs
- CVE-2026-48116
- Confirmed fixed CVEs
- Not specified
- Updated in this feed
- 4 Nov 2026, 03:05 UTC · Revision 1
Source evidence
AnythingLLM: RCE via ripgrep --pre argument injection in filesystem-search-files agent skill
core-osv · Original sourcePublished 28 May 2026, 21:19 UTC
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 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.
osv:CVE-2026-48116
Complete source record
{
"id": "f139e2f7d89d25c1ca3ea5c6453e668bc28315fc8c2bec0149b7b3c740795d6e",
"url": "https://osv.dev/vulnerability/CVE-2026-48116",
"method": "structured",
"payload": {
"kind": "advisory",
"title": "AnythingLLM: RCE via ripgrep --pre argument injection in filesystem-search-files agent skill",
"summary": "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 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.",
"evidence": "osv:CVE-2026-48116",
"products": [],
"severity": "high",
"structured": {
"id": "CVE-2026-48116",
"aliases": [
"CVE-2026-48116",
"GHSA-6hrp-7mw6-8v59"
],
"metrics": [
{
"type": "CVSS_V3",
"score": "CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:H"
}
],
"affected": [
{
"ranges": [
{
"repo": "https://github.com/mintplex-labs/anything-llm",
"type": "GIT",
"events": [
{
"introduced": "0"
},
{
"fixed": "9fe6bbfb09c07628784213e9192a19d2f12bb2a7"
},
{
"fixed": "94ed62d320df1a06c229e4bc3ee09c2cb5111b33"
}
],
"database_specific": {
"extracted_events": [
{
"cpe": "cpe:2.3:a:mintplexlabs:anythingllm:*:*:*:*:*:*:*:*",
"range": [
{
"introduced": "0"
},
{
"fixed": "1.13.0"
}
],
"source": "CPE_RANGE"
},
{
"range": [
{
"fixed": "94ed62d320df1a06c229e4bc3ee09c2cb5111b33"
}
],
"source": "REFERENCES_COMMIT"
}
]
}
}
],
"versions": [
"v1.12.1",
"v1.12.0",
"v1.11.2",
"v1.11.1",
"v1.11.0",
"v1.10.0",
"v1.9.1",
"v1.9.0",
"v1.8.5",
"v1.8.4",
"v1.8.3",
"v1.8.2",
"v1.8.1",
"v1.8.0",
"v1.7.8",
"v1.7.6",
"v1.7.5",
"v1.7.4",
"v1.4.0",
"v1.3.0",
"v1.2.3",
"v1.2.2",
"v1.2.1",
"v1.2.0",
"v1.1.1",
"v1.1.0",
"v1.0.0"
],
"database_specific": {
"source": "https://storage.googleapis.com/cve-osv-conversion/osv-output/CVE-2026-48116.json"
}
}
],
"modified": "2026-10-28T02:30:33.004930589Z",
"provider": "osv",
"references": [
"https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/48xxx/CVE-2026-48116.json",
"https://github.com/Mintplex-Labs/anything-llm/security/advisories/GHSA-6hrp-7mw6-8v59",
"https://nvd.nist.gov/vuln/detail/CVE-2026-48116",
"https://github.com/Mintplex-Labs/anything-llm/commit/94ed62d320df1a06c229e4bc3ee09c2cb5111b33"
],
"provider_metadata": {
"cwe_ids": [
"CWE-77",
"CWE-88"
],
"cna_assigner": "GitHub_M",
"osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/48xxx/CVE-2026-48116.json"
}
},
"related_cves": [
{
"value": "CVE-2026-48116",
"evidence": "/id"
}
],
"security_relevant": true,
"severity_evidence": "/severity/0/score"
},
"source_id": "core-osv",
"document_id": 499877,
"published_at": "2026-05-28T21:19:51.965+00:00"
}