DD openclaw-backup
定期备份 OpenClaw 数据(支持手动/自动/加密备份)。Use when user asks to backup OpenClaw, create backup, save state, protect data, or schedule automatic backups. Triggers: "备份", "backup", "保存数据", "定时备份", "加密备份", "backup to cloud".
As a process D 46/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
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.
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.
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
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 22
-
high Dangerous commands
cmd-persistenceFAQ.md:382Persistence mechanism (cron / launchd / scheduled task / autorun registry)# 创建 ~/Library/LaunchAgents/ai.openclaw.backup.plist
-
high Dangerous commands
cmd-persistencescripts/setup_cron.sh:55Persistence mechanism (cron / launchd / scheduled task / autorun registry)(crontab -l 2>/dev/null; echo "$CRON_EXPR $BACKUP_SCRIPT >> /tmp/openclaw_backup.log 2>&1") | crontab -
-
high Dangerous commands
cmd-persistenceSKILL.md:283Persistence mechanism (cron / launchd / scheduled task / autorun registry)(crontab -l 2>/dev/null; echo "$CRON_EXPR $BACKUP_SCRIPT >> /tmp/openclaw_backup.log 2>&1") | crontab -
Medium and low: 19
-
medium Dangerous commands
cmd-persistencescripts/setup_cron.sh:52Persistence mechanism (cron / launchd / scheduled task / autorun registry) (detector / deny-list definition)crontab -l 2>/dev/null | grep -v "openclaw.*backup" | crontab -
detector -
medium Dangerous commands
cmd-persistenceSKILL.md:279Persistence mechanism (cron / launchd / scheduled task / autorun registry) (detector / deny-list definition)crontab -l 2>/dev/null | grep -v "openclaw.*backup" | crontab -
detector -
low Dangerous commands
cmd-cron-mentionADVANCED.md:404Mentions editing / listing crontab (detector / deny-list definition)env -i HOME=$HOME /bin/bash -c 'crontab -l | grep openclaw'
detector -
low Dangerous commands
cmd-cron-mentionDEMO.md:79Mentions editing / listing crontab查看所有定时任务: crontab -l
-
low Dangerous commands
cmd-cron-mentionDEMO.md:120Mentions editing / listing crontab$ crontab -l
-
low Dangerous commands
cmd-cron-mentionFAQ.md:127Mentions editing / listing crontabcrontab -l
-
low Dangerous commands
cmd-cron-mentionFAQ.md:304Mentions editing / listing crontabcrontab -l
-
low Dangerous commands
cmd-cron-mentionREADME.md:206Mentions editing / listing crontabcrontab -l
-
low Exfiltration
net-credential-usescripts/backup_encrypted.sh:30Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)if [ "$BACKUP_PASSWORD" != "$BACKUP_PASSWORD_CONFIRM" ]; then
quoted -
low Dangerous commands
cmd-cron-mentionscripts/setup_cron.sh:43Mentions editing / listing crontabif crontab -l 2>/dev/null | grep -q "openclaw.*backup"; then
-
low Dangerous commands
cmd-cron-mentionscripts/setup_cron.sh:52Mentions editing / listing crontabcrontab -l 2>/dev/null | grep -v "openclaw.*backup" | crontab -
-
low Dangerous commands
cmd-cron-mentionscripts/setup_cron.sh:55Mentions editing / listing crontab(crontab -l 2>/dev/null; echo "$CRON_EXPR $BACKUP_SCRIPT >> /tmp/openclaw_backup.log 2>&1") | crontab -
-
low Dangerous commands
cmd-cron-mentionscripts/setup_cron.sh:62Mentions editing / listing crontab (string literal in code, not executed)echo "查看所有定时任务: crontab -l"
code literal -
low Exfiltration
net-credential-useSKILL.md:143Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)if [ "$BACKUP_PASSWORD" != "$BACKUP_PASSWORD_CONFIRM" ]; then
quoted -
low Dangerous commands
cmd-cron-mentionSKILL.md:269Mentions editing / listing crontabif crontab -l 2>/dev/null | grep -q "openclaw.*backup"; then
-
low Dangerous commands
cmd-cron-mentionSKILL.md:279Mentions editing / listing crontabcrontab -l 2>/dev/null | grep -v "openclaw.*backup" | crontab -
-
low Dangerous commands
cmd-cron-mentionSKILL.md:283Mentions editing / listing crontab(crontab -l 2>/dev/null; echo "$CRON_EXPR $BACKUP_SCRIPT >> /tmp/openclaw_backup.log 2>&1") | crontab -
-
low Dangerous commands
cmd-cron-mentionSKILL.md:290Mentions editing / listing crontab (quoted — discussed, not commanded)echo "查看所有定时任务: crontab -l"
quoted -
low Dangerous commands
cmd-cron-mentionSKILL.md:468Mentions editing / listing crontabcrontab -l
Files scanned: 12. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 4, column 14: description: 定期备份 OpenClaw 数据(支持手动/自动/加密备份)。Use when user asks to backup OpenCl… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value - note
frontmatter-keyunknown frontmatter key "slug"
Process rating: all ten parameters 46/100
- 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
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 1 mutating operations with no state check
- 40Consistency. Frontmatter name (openclaw-backup) differs from the folder (halaoluan-openclaw-backup)
- 100Tools and files. No external tools needed
- 100Steps. 19 steps
- 100Execution cost. Instruction body is 2252 tokens
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -31 of 5 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +5Description quotes 2 example trigger phrases
- +3Description length 210: enough signal without eating the budget
- +4Structure: 24 headings
- +3Step-by-step instructions: 19 items
- +4Has examples (13 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.