Skip to content
Fencer Intel
high 8.1

CVE-2026-54520 json

AI Agent Automation: Workflow file step path traversal allows read and write outside the expected directory

published 5mo ago modified last mo. also EUVD-2026-82577 , GHSA-cm8g-8jfq-887p

Unreviewed: the maintainers' own advisory

Published by the maintainers on their GitHub repository vmDeshpande/ai-agent-automation. GitHub has not reviewed it into the GitHub Advisory Database, so the affected packages and versions are the maintainers' word. Read the full advisory on GitHub.

cvss
8.1
version 3.1, CNA
cisa kev
Not listed
not in CISA's catalog
epss
0.5%
EPSS 0.5% chance of exploitation in 30 days, percentile 42%
public exploits
0
none known

Summary

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.

Patch / fix

Is CVE-2026-54520 in your stack? Fencer shows which of your repositories are affected as soon as an advisory lands, and opens the fix as a pull request.

Check with Fencer

CISA SSVC

Exploitation
none
Automatable
no
Technical impact
total
Assessed
last mo.

Exploit prediction

0.49% chance of exploitation in the next 30 days, higher than 42% of all scored CVEs (FIRST EPSS, 2026-11-11).

CVSS scores

assigned by version score vector
CNA 3.1 8.1 CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:N

Affected products

  • vmDeshpande ai-agent-automation

Classification

Weakness
  • CWE-22 Improper Limitation of a Pathname to a Restricted Directory

References

Sources

Fencer Intel keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.

The maintainers of vmDeshpande/ai-agent-automation published their own advisory on GitHub. Reviewed sources take precedence over it.