SKILLEMALL.ai
RU Sign in

D github-memory-sync

将 OpenClaw 的完整工作空间配置（SOUL.md, IDENTITY.md, USER.md, MEMORY.md, TOOLS.md, memory/*等）同步到 GitHub 进行备份和版本控制，支持跨服务器迁移。Use when user mentions GitHub backup, sync memory, migrate server, 备份配置，同步到 GitHub, or wants to backup/restore OpenClaw workspace.

Not recommendedcritical or high security findings · low grade D
ClawHub Agent Skills author: Davin Wang v1.1.0 MIT-0 8 files · 2 scripts body ≈ 998 tokens open source ↗ analyzed 28 h ago
ProcedureGitHubInfrastructuretype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
D
58/100
Overall score
Safety 60%
49
Quality 40%
71
Tests bonus
0

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Dangerous commands
If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

How to improve

  1. Review the high-severity findings: each costs 18 safety points. If one is a false positive, allow the rule id under guard.allow in spec.yaml.
  2. The text references missing files: add them or drop the links.
  3. Add evals/evals.json with 4–6 real requests and expected answers: the full check will then use your cases instead of a model draft.
  4. Add a spec.yaml with triggers and assertions (skilltest init): the behaviour contract for CI.

Guard findings · 9

  • high Dangerous commands cmd-persistence CRON.md:106
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    (crontab -l 2>/dev/null; echo "30 2 * * * /root/.openclaw/workspace/skills/github-memory-sync/cron-backup.sh") | crontab -
  • high Dangerous commands cmd-persistence README.md:61
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    (crontab -l 2>/dev/null; echo "30 2 * * * /root/.openclaw/workspace/skills/github-memory-sync/cron-backup.sh") | crontab -
Medium and low: 7
  • medium Dangerous commands cmd-shell-rc CRON.md:101
    Writes to a shell startup file
    echo 'export GITHUBTOKEN="github_pat_xxx"' >> ~/.bashrc
  • medium Dangerous commands cmd-shell-rc CRON.md:102
    Writes to a shell startup file
    echo 'export GITHUB_REPO="davinwang/openclaw-memory"' >> ~/.bashrc
  • low Dangerous commands cmd-cron-mention CRON.md:9
    Mentions editing / listing crontab
    crontab -e
  • low Dangerous commands cmd-cron-mention CRON.md:21
    Mentions editing / listing crontab
    crontab -e
  • low Dangerous commands cmd-cron-mention CRON.md:106
    Mentions editing / listing crontab
    (crontab -l 2>/dev/null; echo "30 2 * * * /root/.openclaw/workspace/skills/github-memory-sync/cron-backup.sh") | crontab -
  • low Dangerous commands cmd-cron-mention CRON.md:109
    Mentions editing / listing crontab
    crontab -l
  • low Dangerous commands cmd-cron-mention README.md:61
    Mentions editing / listing crontab
    (crontab -l 2>/dev/null; echo "30 2 * * * /root/.openclaw/workspace/skills/github-memory-sync/cron-backup.sh") | crontab -

Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.

Lint

  • warning missing-ref reference to a missing file: scripts/sync_to_github.py
  • warning missing-ref reference to a missing file: references/migration-guide.md
  • warning missing-ref reference to a missing file: references/backup-policy.md

Process maturity 35/100

Will not run. References files that are not bundled: scripts/sync_to_github.py, references/migration-guide.md, references/backup-policy.md
  • 0Tools and files. 3 referenced file(s) missing: scripts/sync_to_github.py, references/migration-guide.md, references/backup-policy.md
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 1 mutating operations with no state check
  • 100Steps. 60 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 998 tokens
  • 100Progress reporting. Reports progress
  • low 10 top-level sections: this looks like several domains in one skill

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • -228 emoji in the instructions: noise for the model
  • +2Single-language instructions
  • +3Description length 243: enough signal without eating the budget
  • +4Structure: 30 headings
  • +3Step-by-step instructions: 60 items
  • +4Has examples (10 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 71.

External checks

ClawHub: suspicious
This is a real GitHub backup skill, but it can upload highly sensitive OpenClaw memory and configuration files with weak guardrails and a risky cron default.
LLM: suspicious (high) · VirusTotal: suspicious · 28 May 2026