Severity by source
CVSS:4.0/AV:L/AC:L/AT:N/PR:L/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:P/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
Local-only attack vector with low privileges required; path traversal yields partial file read/write within process scope, no scope change to other systems.
Primary rating from Vendor (VulDB).
CVSS VectorVendor: VulDB
Lifecycle Timeline
3DescriptionCVE.org
A flaw has been found in abrinsmead mindpilot-mcp 0.5.0. Affected by this issue is some unknown functionality of the component HistoryService. This manipulation of the argument ID causes path traversal. The attack needs to be launched locally. The project was informed of the problem early through an issue report but has not responded yet.
AnalysisAI
Path traversal in abrinsmead mindpilot-mcp 0.5.0 allows local low-privileged users to escape intended directory boundaries by supplying crafted path traversal sequences as the ID argument to the HistoryService component, enabling unauthorized file reads and writes within the process's permission scope. Publicly available proof-of-concept exploit code exists (E:P per CVSS 4.0 vector), and the vendor has not responded to coordinated disclosure via GitHub issue #24. No patch is available at time of analysis.
Technical ContextAI
mindpilot-mcp is an MCP (Model Context Protocol) server implementation by developer abrinsmead, identified by CPE cpe:2.3:a:abrinsmead:mindpilot-mcp:*:*:*:*:*:*:*:*. The vulnerability resides in the HistoryService component, where user-supplied input controlling the ID argument is used in file path construction without proper sanitization or canonicalization. CWE-22 (Improper Limitation of a Pathname to a Restricted Directory) describes this root cause class - the application fails to resolve or reject path traversal sequences such as '../', allowing the effective file path to escape the intended directory. MCP servers often interact with local file system resources on behalf of AI agent workflows, making the HistoryService's ID parameter a plausible point of untrusted input entry.
RemediationAI
No vendor-released patch has been identified at time of analysis - the maintainer has not responded to coordinated disclosure submitted via GitHub issue #24. Users should monitor the repository at https://github.com/abrinsmead/mindpilot-mcp/ for a remediation commit or tagged release. As an immediate compensating control, restrict local system access to mindpilot-mcp to only explicitly trusted users, since the AV:L vector means exploitation requires physical or shell-level local access. Additionally, consider confining the mindpilot-mcp process using OS-level sandboxing mechanisms such as AppArmor, SELinux policy, or a chroot jail to limit the file paths reachable via traversal; note that aggressive path restrictions may break legitimate HistoryService functionality and should be tested before deployment. Running the process under a dedicated low-privilege service account with minimal filesystem permissions reduces the blast radius of any successful traversal. The VulDB advisory is available at https://vuldb.com/vuln/387026.
Same weakness CWE-22 – Path Traversal
View allSame technique Path Traversal
View allShare
External POC / Exploit Code
Leaving vuln.today
EUVD-2026-54788
GHSA-6cmv-x2ph-3gc2