FD workspace-git-backup
Set up automatic scheduled backups to GitHub or GitLab. Use when users want to backup their OpenClaw workspace or other directories. Supports GitHub CLI for easy repo creation. Works on macOS (launchd) and Linux (cron).
As a process D 38/100 · 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 · 12
-
high Dangerous commands
cmd-persistencescripts/install-cron.sh:20Persistence mechanism (cron / launchd / scheduled task / autorun registry)(crontab -l 2>/dev/null | grep -v "github-backup.sh") | crontab -
-
high Dangerous commands
cmd-persistencescripts/install-cron.sh:23Persistence mechanism (cron / launchd / scheduled task / autorun registry)(crontab -l 2>/dev/null; echo "$SCHEDULE $BACKUP_SCRIPT >> $LOG_FILE 2>&1") | crontab -
-
high Dangerous commands
cmd-persistencescripts/install-launchd.sh:75Persistence mechanism (cron / launchd / scheduled task / autorun registry)launchctl load "$PLIST"
-
high Dangerous commands
cmd-persistencescripts/manage.sh:139Persistence mechanism (cron / launchd / scheduled task / autorun registry)(crontab -l 2>/dev/null | grep -v "github-backup.sh") | crontab -
Medium and low: 8
-
medium Dangerous commands
cmd-persistencescripts/install-launchd.sh:10Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)PLIST="$HOME/Library/LaunchAgents/com.openclaw.github-backup.plist"
code literal -
medium Dangerous commands
cmd-persistencescripts/manage.sh:10Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)PLIST="$HOME/Library/LaunchAgents/com.openclaw.github-backup.plist"
code literal -
medium Dangerous commands
cmd-persistenceSKILL.md:124Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation table row)| launchd plist | `~/Library/LaunchAgents/com.openclaw.github-backup.plist` |
table -
low Dangerous commands
cmd-cron-mentionscripts/install-cron.sh:20Mentions editing / listing crontab(crontab -l 2>/dev/null | grep -v "github-backup.sh") | crontab -
-
low Dangerous commands
cmd-cron-mentionscripts/install-cron.sh:23Mentions editing / listing crontab(crontab -l 2>/dev/null; echo "$SCHEDULE $BACKUP_SCRIPT >> $LOG_FILE 2>&1") | crontab -
-
low Dangerous commands
cmd-cron-mentionscripts/manage.sh:74Mentions editing / listing crontabif crontab -l 2>/dev/null | grep -q "github-backup.sh"; then
-
low Dangerous commands
cmd-cron-mentionscripts/manage.sh:138Mentions editing / listing crontabif crontab -l 2>/dev/null | grep -q "github-backup.sh"; then
-
low Dangerous commands
cmd-cron-mentionscripts/manage.sh:139Mentions editing / listing crontab(crontab -l 2>/dev/null | grep -v "github-backup.sh") | crontab -
Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 38/100
- 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
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 3 mutating operations with no state check
- 50Steps. 2 steps
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 731 tokens
- 100Progress reporting. Reports progress
- low The response is described with custom markup (3 tags): a typed call is more reliable
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)
- +3No numbered steps or checklist
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 219: enough signal without eating the budget
- +4Structure: 13 headings
- +4Has examples (9 code blocks)
- +3All 4 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.