SKILLEMALL.ai

DC dont-be-scary

Update OpenClaw safely on macOS (brew cask install) with automatic snapshot of the npm package + .app bundle, post-update health check, and automatic rollback to the previous version if the gateway doesn't come back. The update script runs detached so it survives the gateway restart that kills the calling agent. Notifies progress via Telegram at every step (start, success, failure, rollback). Use when the user asks to update OpenClaw, upgrade to a new version, run "openclaw update", or wants protection against a broken update breaking their gateway. Mac-only (requires brew cask install + launchctl). Requires Telegram configured in openclaw.json and ~500MB free in /tmp.

Not recommendedcritical or high security findings · low grade D
ClawHub Agent Skills author: klouddy-cloud v1.0.0 MIT-0 4 files · 1 script body ≈ 837 tokens Open the sourceclawhub.ai analyzed 3 d ago

As a process C 64/100 · Has gaps — weak spots: result and completion, running it twice

IntegrationTelegramAI and agentsInfrastructuretype and topics are labelled automatically from the skill text
JSON
Technical rating
D
41/100
safety, quality, tests
Safety 60%
9
Quality 40%
89
Run on models
none yet
Process rating
C
64/100
Has gaps
Result and completion w 14
0
Running it twice w 4
30
Failures and branches w 10
50
the three weakest of ten parameters · all ten

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. 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.
For the model run — optional
  • 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 · 11

  • high Dangerous commands cmd-persistence references/rescue-prompt.md:28
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    - launchctl bootout gui/$(id -u) ~/Library/LaunchAgents/ai.openclaw.gateway.plist
  • high Dangerous commands cmd-persistence references/rescue-prompt.md:32
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    - launchctl bootstrap gui/$(id -u) ~/Library/LaunchAgents/ai.openclaw.gateway.plist
  • high Dangerous commands cmd-persistence references/rescue-prompt.md:48
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    - LaunchAgent: ~/Library/LaunchAgents/ai.openclaw.gateway.plist
  • high Dangerous commands cmd-persistence scripts/safe-update.sh:106
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl bootstrap "gui/$(id -u)" "$PLIST" 2>/dev/null
Medium and low: 7
  • medium Dangerous commands cmd-persistence scripts/safe-update.sh:22
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (code comment)
    #   OPENCLAW_PLIST        — LaunchAgent plist (default: ~/Library/LaunchAgents/ai.openclaw.gateway.plist)
    comment
  • medium Dangerous commands cmd-persistence scripts/safe-update.sh:31
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
    PLIST="${OPENCLAW_PLIST:-$HOME/Library/LaunchAgents/ai.openclaw.gateway.plist}"
    code literal
  • medium Dangerous commands cmd-persistence SKILL.md:50
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)
    - `OPENCLAW_PLIST` — LaunchAgent (default: `~/Library/LaunchAgents/ai.openclaw.gateway.plist`)
    quoted
  • low Dangerous commands cmd-background-process scripts/safe-update.sh:5
    Starts a background / autostarted process (code comment)
    #   nohup "$OPENCLAW_WORKSPACE_DIR/skills/dont-be-scary/scripts/safe-update.sh" </dev/null >/dev/null 2>&1 & disown
    comment
  • low Exfiltration exfil-webhook-url scripts/safe-update.sh:84
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    curl -s -X POST "https://api.telegram.org/bot${BOT_TOKEN}/sendMessage" \
    placeholder
  • low Exfiltration net-credential-use scripts/safe-update.sh:84
    Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)
    curl -s -X POST "https://api.telegram.org/bot${BOT_TOKEN}/sendMessage" \
    vendor-host
  • low Dangerous commands cmd-background-process SKILL.md:21
    Starts a background / autostarted process
    nohup "<path-to-skill>/scripts/safe-update.sh" </dev/null >/dev/null 2>&1 & disown

Files scanned: 4. 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 64/100

  • 0Result and completion. Does not say what the result is
  • 30Running it twice. 1 mutating operations with no state check
  • 50Failures and branches. 0 branches, has a failure section
  • 60Tools and files. Uses tools (web, node) that frontmatter does not declare
  • 70When it triggers. States when to use, but not when not to
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 100Steps. 24 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 837 tokens
  • 100Progress reporting. Reports progress
  • low The response is described with custom markup (5 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)
  • +3Output format is not stated: the model decides each time
  • -2localhost URLs: will not work for another user
  • +1No license
  • +2Single-language instructions
  • +3Description length 677: enough signal without eating the budget
  • +4Structure: 8 headings
  • +3Step-by-step instructions: 24 items
  • +4Has examples (1 code blocks)
  • +4Reference files are cited in the instructions (1 of 1)
  • +3All 1 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.

External checks

ClawHub: suspicious
This looks like a real OpenClaw update/rescue skill, but it gives agents broad update, restart, deletion, background execution, and Telegram credential-handling authority without enough user control.
LLM: suspicious (medium) · VirusTotal: · 29 May 2026