CD healthy-backup
Health-gated backup for OpenClaw rigs. Audits first — only backs up if healthy. Three tiers, 5-backup retention, optional rclone sync. Sensitive config values scrubbed before staging. Linux/cron native.
As a process D 49/100 · 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.
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 · 9
-
high Dangerous commands
cmd-persistencesetup.sh:141Persistence mechanism (cron / launchd / scheduled task / autorun registry)( crontab -l 2>/dev/null | grep -v "healthy-backup.sh"; echo "$CL" ) | crontab -
Medium and low: 8
-
low Dangerous commands
cmd-cron-mentionhealthy-backup.sh:212Mentions editing / listing crontab[ "$C_CRON" = "true" ] && crontab -l 2>/dev/null \
-
low Dangerous commands
cmd-cron-mentionsetup.sh:141Mentions editing / listing crontab( crontab -l 2>/dev/null | grep -v "healthy-backup.sh"; echo "$CL" ) | crontab -
-
low Dangerous commands
cmd-cron-mentionsetup.sh:143Mentions editing / listing crontab (detector / deny-list definition; string literal in code, not executed)log "Verify: crontab -l | grep healthy-backup"
detectorcode literal -
low Dangerous commands
cmd-cron-mentionsetup.sh:144Mentions editing / listing crontab (detector / deny-list definition; string literal in code, not executed)log "Remove: crontab -l | grep -v healthy-backup.sh | crontab -"
detectorcode literal -
low Dangerous commands
cmd-cron-mentionSKILL.md:73Mentions editing / listing crontab (documentation table row; documentation of a security skill)| `crontab -l` (opt-in, default off) | List cron jobs for DEPENDENCIES.md | VAR=values redacted before writing |
tablesecurity skill -
low Dangerous commands
cmd-privilegeSKILL.md:133Privilege escalation / world-writable permissions (documentation of a security skill)sudo bash rclone-install.sh
security skill -
low Dangerous commands
cmd-cron-mentionSKILL.md:168Mentions editing / listing crontab (documentation of a security skill)crontab -e
security skill
A further 1 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
Process rating: all ten parameters 49/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 4 mutating operations with no state check
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 60Failures and branches. 2 branches
- 85Steps. 6 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2919 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- +1No license
- +2Single-language instructions
- +3Description length 202: enough signal without eating the budget
- +4Structure: 16 headings
- +3Step-by-step instructions: 6 items
- +4Has examples (14 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.