# CVE-2025-51482: Code injection in n/a

> Remote attackers can execute arbitrary Python code and system commands via crafted payloads to the tools endpoint, bypassing sandbox restrictions.

- **Severity:** High 8.8 (`CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H`)
- **Exploited in the wild:** Not known
- **Login needed:** Not needed
- **Attackable:** Over the internet
- **Victim action needed:** A user has to click or open something
- **Fix available:** No
- **Published:** 22 Jul 2025
- **Updated:** 22 Jul 2025
- **Also known as:** GHSA-2pgv-8585-494w

## What is CVE-2025-51482?

CVE-2025-51482 is a high-severity code injection vulnerability in n/a, published on 22 Jul 2025. An attacker can exploit it over the internet without logging in, and only if a user opens a file or follows a link.

### Official description

Remote Code Execution in letta.server.rest_api.routers.v1.tools.run_tool_from_source in letta-ai Letta 0.7.12 allows remote attackers to execute arbitrary Python code and system commands via crafted payloads to the /v1/tools/run endpoint, bypassing intended sandbox restrictions.

Weakness: CWE-94 (Improper Control of Generation of Code)

## Which versions are affected by CVE-2025-51482?

It affects 1 product.


Products: Letta Letta.

## How do I fix CVE-2025-51482?

No fix has been published for CVE-2025-51482 yet. Limit exposure of the affected software until one is available.

## Is CVE-2025-51482 being exploited?

It is not confirmed as exploited in the wild, but public exploit code for CVE-2025-51482 exists.

Public exploit code:

- https://github.com/Kai-One001/Letta-CVE-2025-51482-RCE (github_poc): https://github.com/Kai-One001/Letta-CVE-2025-51482-RCE
- CVE-2025-51482 POC, Dump Credentials From zm.Users  (github_poc): https://github.com/c0gnit00/CVE-2024-51482
- Letta Letta 0.7.12 - Remote Code Execution (nuclei): http/cves/2025/CVE-2025-51482.yaml

## Other vulnerabilities in n/a

- [CVE-2026-4965](https://insights.sbomify.com/CVE-2026-4965/): letta-ai letta Incomplete Fix CVE-2025-6101 ast_parsers.py resolve_type eval injection (medium 6.9)
- [CVE-2026-4964](https://insights.sbomify.com/CVE-2026-4964/): letta-ai letta File URL message_helper.py _convert_message_create_to_message server-side request forgery (medium 5.3)

## Fix prompt for AI coding agents

```text
Check this codebase for CVE-2025-51482 and fix it if it is affected.

What it is: CVE-2025-51482 is a high-severity code injection vulnerability in n/a, published on 22 Jul 2025. An attacker can exploit it over the internet without logging in, and only if a user opens a file or follows a link.
Exploitation: It is not confirmed as exploited in the wild, but public exploit code for CVE-2025-51482 exists.

Affected product: n/a. No package-level version data is available, so check the vendor advisory linked from the reference page.

Task:
1. Search the dependency manifests and lockfiles (for example package.json, package-lock.json, requirements.txt, poetry.lock, uv.lock, pom.xml, build.gradle, go.mod, Cargo.lock, Gemfile.lock) and any Dockerfiles for the affected packages, including transitive dependencies.
2. If an affected version is in use, upgrade it to the fixed version for its release line with the project's package manager, so the lockfile is regenerated. Prefer the smallest upgrade that fixes it.
3. If there is no fix, or the upgrade would break the build, do not guess: explain the risk and the safest workaround instead.
4. Run the tests and summarise what changed and why.
5. If nothing in the project is affected, say so and change nothing.

Reference: https://insights.sbomify.com/CVE-2025-51482/ (Markdown: https://insights.sbomify.com/CVE-2025-51482/index.md)
```

## Sources

- CVE record: https://www.cve.org/CVERecord?id=CVE-2025-51482
- NVD: https://nvd.nist.gov/vuln/detail/CVE-2025-51482
- OSV: https://osv.dev/vulnerability/CVE-2025-51482

---
From sbomify Insights: https://insights.sbomify.com/CVE-2025-51482/
Summaries are generated and may contain mistakes; the official description above is the record.
