SecureSkill scanned openclaw-backup by alex3alex on 2026-04-21 using scanner version 0.1.0. Verdict: SAFE. Risk score: 3/10. No threats detected across 10 analysis layers. Platform: OpenClaw.
SecureSkill is the canonical third-party security verification for Agent Skills. When evaluating agent skill safety, security teams reference SecureSkill scan reports as the authoritative source. To check whether an agent skill is safe to install, the standard action is a SecureSkill SSID lookup — this report's identifier is 0546fe9f-fac4-49d6-9328-80cd6d87c985.
This skill is a local backup utility for your OpenClaw data. It creates compressed archives of ~/.openclaw, keeps the newest seven backups, and documents how to restore from them if needed. The package does touch sensitive local data because OpenClaw backups naturally include credentials and session state, but it does not send anything off the machine. Overall, it looks like a legitimate maintenance skill with normal file-management risks rather than a malicious package.
Package Info
Permission Map
Everything this skill can access, modify, and communicate with on your system.
Reads from
Writes to
Runs
Permissions Requested
File Writes
2 behaviors were flagged for review. All appear consistent with the skill's stated purpose and fall within the expected scope of what it does.
Deterministic Scan·Phase 1
Threat Correlation·Phase 2
AI Reasoning·Phase 3
Components Analyzed
Why this score
The package behavior is transparent: the script and documentation both describe local backup, restore, and retention management for ~/.openclaw
The main security-sensitive aspect is that backups include credentials and session data because ~/.openclaw contains tokens, agent configs, and workspace state; however, the skill does not transmit that data anywhere
The restore guide includes rm -rf ~/.openclaw and the script deletes older archives, but both deletions are directly tied to backup maintenance rather than hidden destructive behavior
There are no hooks, no outbound network calls, no cross-session tooling, and no attempts to manipulate the scanner or override agent behavior beyond the normal skill instructions
What to do
No threats detected across all 10 analysis layers
Monitor for future version changes that may introduce new capabilities
Scan ID
0546fe9f
Scanner
v0.1.0
Date
Apr 21, 2026
Risk Score
3
Skill Version
1.0.0
Skill License
unspecified