SKILLEMALL.ai

BF update-advisor

OpenClaw update check and upgrade assistant. Triggers on phrases like "check for updates", "any new version", "is openclaw updated", "run the update", "confirm update", "upgrade openclaw". Two modes: (1) Check mode — analyze changelog, risk assessment, recommendation; (2) Execute mode — perform update with explicit, pre-update recovery watchdog protection (macOS launchd or Linux systemd).

ClawHub Agent Skills author: kelven.ling v1.1.1 MIT-0 10 files · 5 scripts body ≈ 3 399 tokens Open the sourceclawhub.ai analyzed 2 d ago

As a process F 62/100 · Will not run — References files that are not bundled: scripts/recovery-watchdog-launchd.template.plist

AnalyzerWriting and documentsInfrastructuretype and topics are labelled automatically from the skill text
JSON
Technical rating
B
87/100
safety, quality, tests
Safety 60%
95
Quality 40%
74
Run on models
none yet
Process rating
F
62/100
Will not run
References files that are not bundled: scripts/recovery-watchdog-launchd.template.plist
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
70
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Concealment medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill tells the agent to hide things from you: not to show errors, not to mention actions, to report differently from what was done. You lose the ability to see what the agent really did.

For the author

Transparency beats a smooth answer. If the goal is to hide technical noise, ask the agent to "summarise briefly", not to "not mention".

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. The text references files that are not there: add them or drop the references.
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 · 1

✓ No critical or high findings

Medium and low: 1
  • medium Concealment en-hide-from-user README.md:84
    Instruction to hide actions from the user (security demo / example)
    If OpenClaw was installed by a different OS user (e.g. via Homebrew under another account), running `openclaw update` as the current user may silently install a second copy instead of updating the ori
    demo

Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning missing-ref reference to a missing file: scripts/recovery-watchdog-launchd.template.plist

Process rating: all ten parameters 62/100

Will not run. References files that are not bundled: scripts/recovery-watchdog-launchd.template.plist
  • 0Tools and files. 1 referenced file(s) missing: scripts/recovery-watchdog-launchd.template.plist
  • 0Result and completion. Does not say what the result is
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 85Steps. 44 steps, 1 vague phrases
  • 100When it triggers. States when to use and when not to
  • 100Failures and branches. 13 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 3399 tokens
  • 100Running it twice. Mutating operations check current state
  • 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

  • +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
  • +5Description quotes 6 example trigger phrases
  • +3Description length 391: enough signal without eating the budget
  • +4Structure: 19 headings
  • +3Step-by-step instructions: 44 items
  • +4Has examples (9 code blocks)
  • +3All 5 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.

External checks

ClawHub: suspicious
The skill’s update workflow is mostly disclosed and coherent, but it deserves Review because it can modify OpenClaw, create temporary background recovery jobs, and its cleanup script trusts paths from a local state file.
LLM: suspicious (high) · VirusTotal: · 29 May 2026