CC wtt-skill
WTT (Want To Talk) agent messaging and orchestration skill for OpenClaw with topic/P2P communication, task and pipeline operations, delegation, IM routing, and WebSocket-first autopoll runtime. Use when handling @wtt commands, installing autopoll service, or integrating WTT task updates into chat workflows.
As a process C 52/100 · 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.
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.
- 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 · 12
-
high Dangerous commands
cmd-persistencescripts/install_autopoll.sh:417Persistence mechanism (cron / launchd / scheduled task / autorun registry)if launchctl bootstrap "$d" "$plist" >/dev/null 2>&1; then
Medium and low: 11
-
medium Exfiltration
net-redirectable-api-keyadapter.py:84Helper 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
-
medium Exfiltration
net-redirectable-api-keyhandler.py:942Helper 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
-
medium Dangerous commands
cmd-persistencescripts/install_autopoll.sh:368Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)local plist="$HOME/Library/LaunchAgents/com.openclaw.wtt.autopoll.plist"
code literal -
medium Dangerous commands
cmd-persistencescripts/install_autopoll.sh:465Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)echo " Try: launchctl bootstrap gui/$uid $plist && launchctl kickstart -k gui/$uid/$label"
code literal -
medium Dangerous commands
cmd-persistencescripts/uninstall_autopoll.sh:7Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)plist="$HOME/Library/LaunchAgents/com.openclaw.wtt.autopoll.plist"
code literal -
medium Exfiltration
net-redirectable-api-keystart_wtt_autopoll.py:103Helper 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
-
medium Exfiltration
net-redirectable-api-keywtt_client.py:126Helper 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 Exfiltration
exfil-webhook-urladapter.py:18Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)agent = ClaudeAgent(agent_id="my-agent", webhook_url="https://hooks.slack.com/...")
placeholder -
low Exfiltration
read-dotenvREADME.md:44Reads a .env filecp ~/.openclaw/workspace/skills/wtt-skill/.env.example ~/.openclaw/workspace/skills/wtt-skill/.env
-
low Dangerous commands
cmd-background-processscripts/install_autopoll.sh:451Starts a background / autostarted processnohup "$WRAPPER_SCRIPT" >/tmp/wtt_autopoll.log 2>/tmp/wtt_autopoll_error.log &
-
low Exfiltration
read-dotenvSKILL.md:213Reads a .env filecp ~/.openclaw/workspace/skills/wtt-skill/.env.example ~/.openclaw/workspace/skills/wtt-skill/.env
Files scanned: 16. 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 52/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 15 mutating operations with no state check
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 70Execution cost. Instruction body is 4704 tokens
- 100Steps. 111 steps
- 100Failures and branches. 3 branches, has a failure section
- 100Consistency. Name and required fields are in place
- low The response is described with custom markup (17 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
- +1No license
- +2Single-language instructions
- +3Description length 308: enough signal without eating the budget
- +4Structure: 37 headings
- +3Step-by-step instructions: 111 items
- +4Has examples (24 code blocks)
- +3All 3 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.