CB world2agent-manage
Install, list, and remove World2Agent sensors on this OpenClaw machine via the openclaw-sensor-bridge supervisor (out-of-process; signals POST to /hooks/agent). Trigger whenever the user wants to subscribe to / watch / be notified about an outside-world source (Hacker News, GitHub, X, market data, RSS, papers, etc.) or wants to manage their existing W2A sensors.
As a process B 73/100 · Nearly there — weak spots: 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 · 6
-
high Dangerous commands
cmd-persistencescripts/install-launchd.sh:54Persistence mechanism (cron / launchd / scheduled task / autorun registry)launchctl bootstrap "gui/$(id -u)" "$PLIST" >/dev/null 2>&1 \
Medium and low: 5
-
medium Dangerous commands
cmd-persistencescripts/_lib.sh:49Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)printf '%s/Library/LaunchAgents/%s.plist' "$HOME" "$LAUNCHD_LABEL"
code literal -
medium Dangerous commands
cmd-persistencescripts/install-launchd.sh:9Persistence mechanism (cron / launchd / scheduled task / autorun registry) (code comment)# Exit: 0 ok / 1 not on macOS, binary missing, launchctl bootstrap failed
comment -
low Dangerous commands
cmd-persistencescripts/install-launchd.sh:55Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed; documentation table row)|| out_err "launchctl bootstrap $PLIST failed"
code literaltable -
low Dangerous commands
cmd-background-processscripts/start.sh:41Starts a background / autostarted processnohup "$binary" --foreground >>"$log" 2>&1 </dev/null &
-
low Dangerous commands
cmd-background-processscripts/start.sh:42Starts a background / autostarted processdisown 2>/dev/null || true
Files scanned: 15. 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 73/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 100Steps. 22 steps
- 100Failures and branches. 8 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3902 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
- low 12 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (12 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)
- -4Absolute local paths (C:\Users, /home/…): not portable
- -31 of 13 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 364: enough signal without eating the budget
- +4Structure: 19 headings
- +3Step-by-step instructions: 22 items
- +3Output format is stated explicitly
- +4Has examples (18 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.