gstack is an AI agent skill, created by garrytan and published at garrytan/gstack. ClawSecure audited gstack across 59 files through the 3-Layer Audit Protocol covering all ten OWASP ASI Top 10 categories, assigning a security score of 0/100 (High Risk). The 13 findings concentrate in Command Injection, Malicious Code and Policy Violation, including Pattern detected: from "child_process" and Pattern detected: execSync(. 6 were rated high or critical severity.
Is gstack safe?
ClawSecure audited gstack and assigned a security score of 0/100 (High Risk), identifying 13 findings across Command Injection and Malicious Code. Review the findings below before installing.
What did ClawSecure find in gstack?
ClawSecure identified 13 findings in gstack, concentrated in Command Injection, Malicious Code and Policy Violation. 6 were rated high or critical severity. The most severe include Pattern detected: from "child_process" and Pattern detected: execSync(.
How was gstack audited?
ClawSecure ran gstack through its 3-Layer Audit Protocol with full OWASP ASI Top 10 coverage, scanning 59 files from garrytan/gstack.
What does a score of 0 mean?
ClawSecure assigned gstack a security score of 0/100, placing it in the High Risk range. This is driven by 13 findings led by Command Injection that should be addressed before use. ClawSecure derives this score with a weighted deduction model (critical -20, high -10, medium -5, low -2 from a base of 100).
Audit Findings for gstack
ClawSecure detected 13 security findings in gstack, spanning Command Injection, Malicious Code, Policy Violation and Obfuscation.
- critical · Pattern detected: from "child_process". Command Injection finding detected in
bin/gstack-global-discover.ts:14. - critical · Pattern detected: execSync(. Command Injection finding detected in
bin/gstack-global-discover.ts:163. - critical · Suspicious domain detected: webhook.site (potential data exfiltration). Malicious Code finding detected in
CHANGELOG.md. - high · Pattern detected: find ~/.gstack/sessions -mmin +120 -type f -exec. Command Injection finding detected in
SKILL.md:12. - high · Attempts to access sensitive file: SOUL.md. Malicious Code finding detected in
CHANGELOG.md. - high · Attempts to access sensitive file: .ssh/. Malicious Code finding detected in
CHANGELOG.md. - medium · Variable $tmpfile (line 4) flows to `curl` at line 5.. Command Injection finding detected in
SKILL.md:473. - medium · Variable $BUN_VERSION (line 13) flows to `bash` at line 13.. Command Injection finding detected in
SKILL.md:481. - medium · File 'SKILL.md' extension (.md) suggests one format but Magika detected.... Obfuscation finding detected in
autoplan/SKILL.md. - medium · Variable $tmpfile (line 4) flows to `curl` at line 5.. Command Injection finding detected in
benchmark/SKILL.md:455. - medium · Variable $BUN_VERSION (line 13) flows to `bash` at line 13.. Command Injection finding detected in
benchmark/SKILL.md:463. - medium · Missing config.json - agent may not be properly configured. Permissions Manifest finding.
Showing the 12 highest-severity of 13 findings. The full interactive list appears below.
3-Layer Audit Protocol
Security Recommendations for gstack
Harden command execution
Audit external network connections
Resolve policy violations
Related Security Research
Why Generic Scanners Fail at AI Agent Security→Understanding Our 3-Layer Audit Protocol→Related AI Agent Security Audits
Scanned on April 17, 2026. gstack is one of thousands of agents audited by ClawSecure from the community-curated awesome-openclaw-skills list and the openclaw/skills repository.