PatchSiren

PatchSiren cyber security CVE debrief

CVE-2026-72718 aaif-goose CVE debrief

CVE-2026-72718 is a high-severity vulnerability in the goose AI agent that allows arbitrary command execution when reviewing a malicious repository. The issue is fixed in version 1.44.0. Affected users should upgrade to prevent exploitation. The vulnerability arises from the `goose review` command running the system `git` executable without stripping attacker-controlled Git configuration, allowing a malicious repository to execute arbitrary commands on the host during the index refresh performed by `git diff HEAD`.

Vendor
aaif-goose
Product
goose
CVSS
HIGH 7
CISA KEV
Not listed in stored evidence
Original CVE published
2026-08-10
Original CVE updated
2026-09-09
Advisory published
2026-08-10
Advisory updated
2026-09-09

Who should care

Users of goose AI agent versions prior to 1.44.0, particularly those who review repositories from untrusted sources, should be aware of this vulnerability and take steps to mitigate it. Affected users should upgrade to version 1.44.0 or later and restrict access to trusted repositories. Additionally, users should monitor for suspicious activity and review compensating controls for exposed systems.

Why it matters

CVE-2026-72718 is a high-severity vulnerability in the goose AI agent that allows arbitrary command execution when reviewing a malicious repository. Users of affected versions should upgrade to 1.44.0 or later and restrict access to trusted repositories.

  • File access or modification with user privileges
  • Exfiltration of environment secrets and provider API keys
  • Potential for lateral movement within the network
  • Verification of repository trust and Git configuration

Technical summary

The `goose review` command runs the system `git` executable to gather the diff for review without stripping attacker-controlled Git configuration. A malicious repository can execute arbitrary commands on the host during the index refresh performed by `git diff HEAD`. The issue is fixed in version 1.44.0. Users of affected versions should upgrade to prevent exploitation. The vulnerability allows for file access or modification with user privileges, exfiltration of environment secrets and provider API keys, and potential for lateral movement within the network.

Defensive priority

High priority for users of goose AI agent versions prior to 1.44.0

Recommended defensive actions

  • Upgrade goose to version 1.44.0 or later
  • Restrict access to trusted repositories
  • Monitor for suspicious activity
  • Review compensating controls for exposed systems while remediation is scheduled and verified
  • Check relevant monitoring, detection, and logs for exposed assets that need extra review
  • Track exceptions, retest remediated assets, and close the item only after evidence is documented
  • Confirm whether affected product deployments exist in managed environments and assign an owner for follow-up

Evidence notes

The vulnerability is caused by the `goose review` command running the system `git` executable without stripping attacker-controlled Git configuration. A malicious repository can execute arbitrary commands on the host during the index refresh performed by `git diff HEAD`. The issue is fixed in version 1.44.0. Users should verify their current version and upgrade if necessary. The vulnerability allows for file access or modification with user privileges, exfiltration of environment secrets and provider API keys, and potential for latera

Sources and references

Verified primary and authoritative sources

  • CVE-2026-72718 CVE Program record

    Publisher, destination, and source semantics verified

    URL: https://www.cve.org/CVERecord?id=CVE-2026-72718

    CVE Program - Official CVE Program record with source-provided CVE metadata.

  • CVE-2026-72718 NVD vulnerability detail

    Publisher, destination, and source semantics verified

    URL: https://nvd.nist.gov/vuln/detail/CVE-2026-72718

    NIST National Vulnerability Database - Official NIST NVD detail page and source-specific vulnerability assessment.

Supplemental references

Methodology and review provenance

AI-assisted synthesis based on stored public vulnerability evidence. System validation, approval state, and publication status do not by themselves establish human review of this revision. PatchSiren helps prioritize defensive review and does not prove exposure or remediation on any system.