BC smart-updater
Intelligent upgrade management for OpenClaw skills, extensions, and core. HITL (Human-in-the-Loop) mode: scan installed assets, read changelogs, analyze risk, recommend upgrades, then execute only what the user approves. Use when: (1) user asks to check for updates or 检查升级, (2) user asks what's installed or 装了什么, (3) user wants to upgrade a specific skill/extension/plugin, (4) user mentions update/upgrade/版本/新版本, (5) periodic upgrade check via cron. Covers npm packages, ClawHub skills, GitHub-cloned skills, and OpenClaw core.
As a process C 58/100 · Has gaps — 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 · 2
-
high Dangerous commands
cmd-persistencereferences/three-gates.md:60Persistence mechanism (cron / launchd / scheduled task / autorun registry)cp ~/.openclaw/plist-backup/ai.openclaw.gateway.plist ~/Library/LaunchAgents/
Medium and low: 1
-
medium Dangerous commands
cmd-persistencescripts/upgrade.sh:12Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)GATEWAY_PLIST="${HOME}/Library/LaunchAgents/ai.openclaw.gateway.plist"code literal
Files scanned: 9. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "changelog"
Process rating: all ten parameters 58/100
- 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
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 100Steps. 20 steps
- 100Failures and branches. 3 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1353 tokens
- 100Running it twice. No mutating operations
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 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)
- +3Output format is not stated: the model decides each time
- -31 of 3 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 531: enough signal without eating the budget
- +4Structure: 17 headings
- +3Step-by-step instructions: 20 items
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (2 of 3)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.