CF autothread
Add `/topic` to the start of any message and the agent creates a topic/thread from it with an auto-generated title. Telegram and Nicegram: a forum topic is created via the Bot API and the original message is quoted inside it (media is forwarded). Discord: a public thread is created from the message and the quote is posted inside. Signal has no native topics or threads, so its adapter instead posts a titled digest message to the group (or as a DM to a phone number) — no topic object is created there. All credentials are read from the local OpenClaw config; nothing is sent anywhere except the target platform's own API. Each platform adapter is a separate script that implements only its own platform; scripts/ shared helpers handle title fallback and JSON output. The repo also ships an offline test suite with a localhost mock API server (not part of the runtime).
Add /topic to the start of any message and the agent creates a topic/thread from it with an auto-generated title.
As a process F 40/100 · Will not run — References files that are not bundled: <link>
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
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.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The text references files that are not there: add them or drop the references.
- 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 · 5
✓ No critical or high findings
Medium and low: 5
-
medium Exfiltration
net-credential-usescripts/autothread-discord.sh:75Credential used in a network call (verify the destination is the intended service)CHANNEL_INFO=$(curl -s -H "Authorization: Bot ${BOT_TOKEN}" "$API_BASE/channels/${CHANNEL_ID}") -
medium Exfiltration
net-credential-usescripts/autothread-telegram.sh:81Credential used in a network call (verify the destination is the intended service)CREATE_RESULT=$(curl -s "$API/bot${BOT_TOKEN}/createForumTopic" \ -
medium Exfiltration
net-credential-usescripts/autothread-telegram.sh:101Credential used in a network call (verify the destination is the intended service)SEND_RESULT=$(curl -s "$API/bot${BOT_TOKEN}/sendMessage" \ -
medium Exfiltration
net-credential-usescripts/autothread-telegram.sh:113Credential used in a network call (verify the destination is the intended service)FWD_RESULT=$(curl -s "$API/bot${BOT_TOKEN}/forwardMessage" \ -
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bash(curl)allowed-tools: Bash(scripts/autothread-telegram.sh) Bash(scripts/autothread-discord.sh) Bash(scripts/autothread-signal.sh) Bash(scripts/autothread-nicegram.sh) Bash(curl) Bash(jq) Bash(signal-cli) Bas
Files scanned: 9. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
missing-refreference to a missing file: <link>
Process rating: all ten parameters 40/100
- 0Tools and files. 1 referenced file(s) missing: <link>
- 0Result and completion. Does not say what the result is
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 9 mutating operations with no state check
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 16 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 982 tokens
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)
- +3Description length 871: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +4Structure: 6 headings
- +3Step-by-step instructions: 16 items
- +4Has examples (5 code blocks)
- +3All 4 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 67.