CF oref-native
Israeli Home Front Command alerts - fully OpenClaw native. No Home Assistant. No wacli. No Docker monitor. OpenClaw handles everything: WhatsApp + TTS.
As a process F 34/100 · Will not run — weak spots: steps, result and completion, when it triggers
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.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
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 · 6
-
high Dangerous commands
cmd-persistenceinstall.sh:95Persistence mechanism (cron / launchd / scheduled task / autorun registry)(crontab -l 2>/dev/null | grep -v oref_native; echo "$CRON_CMD") | crontab -
-
high Dangerous commands
cmd-persistenceSKILL.md:39Persistence mechanism (cron / launchd / scheduled task / autorun registry)@reboot python3 /root/.openclaw/workspace/skills/oref-native/oref_native.py >> /var/log/oref_native.log 2>&1
Medium and low: 4
-
medium Exfiltration
net-redirectable-api-keyoref_native.py:24Helper sends the API key to a host configured by an environment variable — the key can be redirected to another serverAPI key + configurable base URL from environment
-
low Dangerous commands
cmd-background-processinstall.sh:81Starts a background / autostarted processnohup python3 "$SCRIPT_DIR/oref_native.py" >> "$LOG_FILE" 2>&1 &
-
low Dangerous commands
cmd-persistenceinstall.sh:94Persistence mechanism (cron / launchd / scheduled task / autorun registry) (detector / deny-list definition; string literal in code, not executed)CRON_CMD="@reboot $ENV_EXPORTS python3 $SCRIPT_DIR/oref_native.py >> $LOG_FILE 2>&1 &"
detectorcode literal -
low Dangerous commands
cmd-cron-mentioninstall.sh:95Mentions editing / listing crontab(crontab -l 2>/dev/null | grep -v oref_native; echo "$CRON_CMD") | crontab -
Files scanned: 5. 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 34/100
- 0Steps. Prose only: no discrete steps
- 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
- 40Consistency. Frontmatter name (oref-native) differs from the folder (openclaw-skill-red-alert)
- 100Tools and files. No external tools needed
- 100Execution cost. Instruction body is 355 tokens
- 100Running it twice. No mutating operations
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
- -2localhost URLs: will not work for another user
- -217 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 151: enough signal without eating the budget
- +4Structure: 6 headings
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 65.