MediumVulnerabilityLLM-specific
CVE-2026-82233: SiYuan path traversal in asset.upload MCP tool via absolute file paths
- Source
- NVD(opens in a new tab)
- Identifier
- CVE-2026-82233
- Published
- Record updated
- Known exploitation
- Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
- EPSS
- 0.4%
Summary
SiYuan before v3.8.1 has a path traversal flaw in its asset.upload MCP tool. The tool accepts arbitrary absolute file paths without validating them against the workspace boundary. An attacker can use prompt injection to make the AI Agent copy sensitive files such as SSH keys or credentials from outside the workspace into the asset directory.
Mitigation
The source does not state a fix yet. Check the original advisory for updates.
Topics
Related items
- InfoTop agent skill security resources — November 2026Similar attack · Adversa AI Blog
- InfoHow to Turn AI Red Team Findings Into Runtime ControlsSimilar attack · Straiker Blog
- MediumDocker Sandboxes vulnerability lets AI agents access sensitive files outside their sandbox (CVE-2026-103916) | Endor LabsSimilar attack · Endor Labs Blog
- MediumFree the Model, Sell the Gateway: Prompt Adware hidden in Jailbreak BundlesSimilar attack · Check Point Research
- InfoRight Tool, Wrong Parameters: Defending LLM Agents Against Parameter PoisoningSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)