Vulnerability · Published Sep 17, 2026 · Assigned by GitHub_M
CVE-2026-54520AI Agent Automation: Workflow file step path traversal allows read and write outside the expected directory
High 8.1
In plain English
A high-severity path traversal in ai-agent-automation from vmDeshpande. There are no confirmed reports of exploitation so far. The chance it is exploited in the next 30 days is estimated at 0.5% (higher than 42% of all known vulnerabilities). Ready-made attack tooling exists: public proof-of-concept code.
Official description
AI Agent Automation is a modular AI agent workflow automation platform with schedulers, tools, and observability. Prior to 0.9.1, the executeStep file-step implementation in backend/src/agents/executor.js passes the user-controlled step.path value through path.resolve with process.cwd() and then uses the resulting path for read or write operations without checking that it remains in an approved workflow directory. An authenticated user who can create or modify workflow file steps can supply traversal segments to escape the intended workspace and read sensitive files or write and overwrite files accessible to the backend process, including application-adjacent files when process permissions allow. This issue is fixed in version 0.9.1.
Affected products (as reported)
| Vendor | Product | Versions |
|---|---|---|
| vmDeshpande | ai-agent-automation | < 0.9.1 |
Weakness: CWE-22 · Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:N
References
- https://github.com/vmDeshpande/ai-agent-automation/security/advisories/GHSA-cm8g-8jfq-887p x_refsource_CONFIRM
- https://github.com/vmDeshpande/ai-agent-automation/commit/f49ec7e85a6896b14c275222362e6ce4d445b783 x_refsource_MISC
- https://github.com/vmDeshpande/ai-agent-automation/releases/tag/v0.9.1 x_refsource_MISC