CVE-2026-48116
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…
Does this matter?
High impact if exploited, but EPSS currently rates exploitation as unlikely (0.37%). Schedule it in the normal patch cycle and watch for a rise in EPSS or a public exploit.
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 3.1
- 8.8 HIGHCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
- EPSS
- 0.37% probability · 30th percentile
- CISA KEV
- Not listed
- Weakness
- CWE-77, CWE-88
- Affected
- mintplexlabs/anythingllm
- Source
- security-advisories@github.com
References
- https://github.com/Mintplex-Labs/anything-llm/commit/94ed62d320df1a06c229e4bc3ee09c2cb5111b33Patch
- https://github.com/Mintplex-Labs/anything-llm/security/advisories/GHSA-6hrp-7mw6-8v59Exploit, Mitigation, Vendor Advisory
- https://github.com/Mintplex-Labs/anything-llm/security/advisories/GHSA-6hrp-7mw6-8v59Exploit, Mitigation, Vendor Advisory
Source: NVD record, EPSS from FIRST.org, KEV from CISA. Refreshed daily.