# Vibe-Trading LLM-callable tools permit command execution, code injection, and SSRF Advisory record · `GHSA-jqmf-mx4f-hfr6` - **Identifiers:** `GHSA-jqmf-mx4f-hfr6` · `CVE-2026-114107` - **State:** Confirmed - **Severity:** CVSS 8.7 High - **Critical:** No - **Weakness (CWE):** [CWE-77](https://cwe.mitre.org/data/definitions/77.html) · [CWE-78](https://cwe.mitre.org/data/definitions/78.html) · [CWE-94](https://cwe.mitre.org/data/definitions/94.html) · [CWE-116](https://cwe.mitre.org/data/definitions/116.html) · [CWE-918](https://cwe.mitre.org/data/definitions/918.html) · [CWE-1427](https://cwe.mitre.org/data/definitions/1427.html) - **Tags:** [Command injection](https://agentprime.io/advisories/tag/command-injection.md) · [Code injection](https://agentprime.io/advisories/tag/code-injection.md) · [Server-side request forgery (SSRF)](https://agentprime.io/advisories/tag/ssrf.md) · [CWE-116](https://agentprime.io/advisories/tag/cwe-116.md) · [CWE-1427](https://agentprime.io/advisories/tag/cwe-1427.md) - **Published:** 2 Oct 2026 - **Updated:** 21 Oct 2026 - **Reviewed by a person:** No Published by the GitHub Advisory Database at 2 Oct 2026, 22:44 UTC. agentprime has not analysed this yet, so whether it affects any app is not known. ## Affected packages - `vibe-trading-ai` (PyPI): affected `>=0.1.0, <0.1.7`; fixed in `0.1.7` ## Machine-written summary Summary written by Claude Haiku from the source advisory. Not reviewed by a person. > Vibe-Trading (PyPI package vibe-trading-ai) versions >=0.1.0 and <0.1.7 expose LLM-callable tools that allow command execution, code injection, and server-side request forgery. An attacker who can reach the agent's message endpoint, or who can get the agent to process attacker-controlled content such as a document or web page, can cause the LLM to run arbitrary shell commands, which the source says run as root in the default container. Upgrade to vibe-trading-ai 0.1.7 or later. Written 1 Nov 2026. ## Not analysed yet We haven’t published our analysis of this Advisory yet. Once a person has reviewed it, this page will say what’s vulnerable, what has to be true for your app to be affected, and how to check. ## Severity and exploitation - 8.7 High, CVSS 4.0: `CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N`, from CNA (VulnCheck) - **CISA KEV:** Not listed. - **EPSS:** 0.0058, the 47th percentile, on 5 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days. ## Timeline - 31 Oct 2026, 14:08 UTC: First seen by agentprime - 31 Oct 2026, 14:08 UTC: [Confirmed by OSV](https://osv.dev/vulnerability/GHSA-jqmf-mx4f-hfr6) ## Sources - [GitHub Advisory Database: GHSA-jqmf-mx4f-hfr6](https://github.com/advisories/GHSA-jqmf-mx4f-hfr6) - [OSV: GHSA-jqmf-mx4f-hfr6](https://osv.dev/vulnerability/GHSA-jqmf-mx4f-hfr6) - - - - Facts on this page come from the GitHub Advisory Database (CC-BY 4.0), OSV and the other sources listed, as published. We don’t reproduce full advisory descriptions, which can contain exploit code. ## Check whether this affects you A Match means an installed version is in the affected range above. Most don’t affect the app; agentprime hasn’t analysed this one yet. - With the agentprime MCP server (), ask your agent to check the project: `check_lockfile` sends a lockfile, `check_packages` a list of installed packages, and both return the Matches and the upgrades that clear them. `get_advisory` returns this record. Setup: - In a browser: reads your lockfile in the browser, never uploading it. - Whether it touches your code, with file and line: the Claude Code plugin, - As JSON: , or `POST https://api.agentprime.io/v1/match` with your packages () --- The web page: . Everything for agents: .