High severity · published May 28, 2026
CVE-2026-48116
AnythingLLM: RCE via ripgrep --pre argument injection in filesystem-search-files agent skill
8.8
CVSS
0.4%
EPSS
No
On KEV
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.
CVSS vector
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Attack vector
Network
Complexity
Low
Privileges
Low
User interaction
None
Confidentiality
High
Integrity
High
Availability
High
Scope
Unchanged
Exploitation
Is it being used?
Exploit prediction (EPSS)0.4% · higher than 30% of CVEs
Exploited in the wildNo evidence yet
CISA KEVNot listed
Ransomware campaign useNot known
Affected products
Which versions
AN
anything-llm · Mintplex-Labs
< 1.13.0 · source: vendor
AN
Anythingllm · Mintplexlabs
before 1.13.0 · source: NVD
References
NVD
https://nvd.nist.gov/vuln/detail/CVE-2026-48116
CVE.org
https://www.cve.org/CVERecord?id=CVE-2026-48116
Patch
https://github.com/Mintplex-Labs/anything-llm/commit/94ed62d320df1a06c229e4bc3ee09c2cb5111b33
Exploit
https://github.com/Mintplex-Labs/anything-llm/security/advisories/GHSA-6hrp-7mw6-8v59
More from anything-llm
9.6
CVE-2026-32626
AnythingLLM has a Streaming Phase XSS to RCE via LLM Response Injection
8.8
CVE-2026-32628
AnythingLLM has SQL Injection in Built-in SQL Agent Plugin via Unsanitized table_name Parameter
7.5
CVE-2026-32617
AnythingLLM Permissable CORS policy
7.5
CVE-2026-24477
AnythingLLM has key leak in `systemSettings.js`
7.5
CVE-2024-22422
Unauthenticated Denial of Service (DOS) attack in AnythingLLM
