CVE-2026-72718: CWE-94: Improper Control of Generation of Code ('Code Injection') in aaif-goose goose
goose is general-purpose AI agent that runs on your machine. Prior to 1.44.0, the `goose review` command runs the system `git` executable to gather the diff for review without stripping attacker-controlled Git configuration. A malicious repository whose `.git/config` sets [`core] fsmonitor = <command>` causes Git to execute that command on the host during the index refresh performed by `git diff HEAD`. The command runs before goose contacts a model and without a submitted prompt, model call, tool approval, or trust prompt. The context-gathering Git process is not sandboxed and is outside goose's tool-permission model. Arbitrary commands run with the privileges and environment of the user running goose, allowing file access or modification and exfiltration of environment secrets and provider API keys. The vulnerable Git invocations are built by git_command() in crates/goose-cli/src/commands/review/handler.rs and are used by touched_files() and collect_diff() for `git diff --name-only HEAD` and `git diff HEAD`. This issue is fixed in version 1.44.0.
AI Analysis
Technical Summary
The vulnerability in aaif-goose's goose agent involves the 'goose review' command invoking 'git diff HEAD' to gather diffs without stripping attacker-controlled Git configuration. A malicious repository can set 'core.fsmonitor' to an arbitrary command, which Git executes during its index refresh. This command runs before any model interaction or user approval and outside of goose's tool-permission model, enabling arbitrary code execution with the user's privileges. The vulnerable Git invocations are implemented in the git_command() function in the source code and affect versions prior to 1.44.0. The issue is addressed in version 1.44.0.
Potential Impact
An attacker controlling a malicious Git repository can execute arbitrary commands on the host machine with the privileges of the user running goose. This can lead to unauthorized file access or modification and exfiltration of environment secrets and API keys. The vulnerability does not require user interaction beyond running 'goose review' on the malicious repository. The CVSS 4.0 score is 7 (high severity), reflecting the local attack vector, low attack complexity, required user interaction, and high impact on confidentiality, integrity, and availability.
Mitigation Recommendations
Upgrade to aaif-goose goose version 1.44.0 or later, where this vulnerability is fixed. There is no official patch or temporary fix detailed beyond upgrading. Until then, avoid running 'goose review' on untrusted or potentially malicious Git repositories to prevent arbitrary command execution.
CVE-2026-72718: CWE-94: Improper Control of Generation of Code ('Code Injection') in aaif-goose goose
Description
goose is general-purpose AI agent that runs on your machine. Prior to 1.44.0, the `goose review` command runs the system `git` executable to gather the diff for review without stripping attacker-controlled Git configuration. A malicious repository whose `.git/config` sets [`core] fsmonitor = <command>` causes Git to execute that command on the host during the index refresh performed by `git diff HEAD`. The command runs before goose contacts a model and without a submitted prompt, model call, tool approval, or trust prompt. The context-gathering Git process is not sandboxed and is outside goose's tool-permission model. Arbitrary commands run with the privileges and environment of the user running goose, allowing file access or modification and exfiltration of environment secrets and provider API keys. The vulnerable Git invocations are built by git_command() in crates/goose-cli/src/commands/review/handler.rs and are used by touched_files() and collect_diff() for `git diff --name-only HEAD` and `git diff HEAD`. This issue is fixed in version 1.44.0.
CVSS v4.0
Score 7.0high
Affected software
aaif-goose
goose
pkg:cargo/github/aaif-goose/gooseRun on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.
Weaknesses
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
The vulnerability in aaif-goose's goose agent involves the 'goose review' command invoking 'git diff HEAD' to gather diffs without stripping attacker-controlled Git configuration. A malicious repository can set 'core.fsmonitor' to an arbitrary command, which Git executes during its index refresh. This command runs before any model interaction or user approval and outside of goose's tool-permission model, enabling arbitrary code execution with the user's privileges. The vulnerable Git invocations are implemented in the git_command() function in the source code and affect versions prior to 1.44.0. The issue is addressed in version 1.44.0.
Potential Impact
An attacker controlling a malicious Git repository can execute arbitrary commands on the host machine with the privileges of the user running goose. This can lead to unauthorized file access or modification and exfiltration of environment secrets and API keys. The vulnerability does not require user interaction beyond running 'goose review' on the malicious repository. The CVSS 4.0 score is 7 (high severity), reflecting the local attack vector, low attack complexity, required user interaction, and high impact on confidentiality, integrity, and availability.
Mitigation Recommendations
Upgrade to aaif-goose goose version 1.44.0 or later, where this vulnerability is fixed. There is no official patch or temporary fix detailed beyond upgrading. Until then, avoid running 'goose review' on untrusted or potentially malicious Git repositories to prevent arbitrary command execution.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- GitHub_M
- Date Reserved
- 2026-08-10T13:48:09.545Z
- Cvss Version
- 4.0
- State
- PUBLISHED
Threat ID: 6a7a065cbf8831d53937080d
Added to database: 08/10/2026, 17:11:56 UTC
Last enriched: 08/10/2026, 17:26:14 UTC
Last updated: 09/23/2026, 10:17:47 UTC
Views: 80
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.