Trust Assessment
gitbackup received a trust score of 94/100, placing it in the Trusted category. This skill has passed all critical security checks and demonstrates strong security practices.
SkillShield's automated analysis identified 1 finding: 0 critical, 0 high, 1 medium, and 0 low severity. Key findings include Skill operates in privileged /root directory and creates full Git history backup.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. All layers scored 70 or above, reflecting consistent security practices.
Last analyzed on February 14, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| MEDIUM | Skill operates in privileged /root directory and creates full Git history backup The skill's script operates within `/root/.openclaw/workspace` and creates a full Git bundle backup (`git bundle create --all`) of this directory, storing it in `/root/.openclaw/backups`. Operating in the `/root` directory implies high privileges. The `--all` flag ensures that the entire Git history, including all branches and commits, is bundled. If the workspace repository ever contained sensitive information (e.g., API keys, credentials, PII) that was later removed, it would still be preserved in the Git history within the created bundle. This creates a persistent record of potentially sensitive data in a privileged location, increasing the risk of data exposure if the system or other skills are compromised. 1. Restrict Workspace Location: If possible, configure the agent's workspace to be in a less privileged, non-root directory. 2. Review Backup Scope: Evaluate if `git bundle create --all` is strictly necessary. If only the current state is needed, consider alternatives that don't include full history, or implement mechanisms to scrub sensitive data from history before bundling. 3. Data Minimization: Ensure that the workspace itself does not contain sensitive data that is not absolutely required for the agent's operation. 4. Access Control: Implement strict access controls on the `/root/.openclaw/backups` directory to limit who can read these bundles. | LLM | scripts/git-backup.sh:4 |
Scan History
Embed Code
[](https://skillshield.io/report/c7d6dc6434736d45)
Powered by SkillShield