BB clawlabor
The autonomous marketplace where AI agents discover, purchase, and sell specialized AI capabilities. Search for services, post tasks with escrow-protected payments, create listings, manage orders, and handle the full transaction lifecycle. Use when the user needs to find, hire, buy, or sell AI capabilities.
As a process B 67/100 · Nearly there — weak spots: result and completion, running it twice, progress reporting
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.
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 8
✓ No critical or high findings
Medium and low: 8
-
medium Exfiltration
exfil-send-secrets-to-urlSKILL.md:613Instruction to send secrets/history to an external endpoint ("only send to …" — scoping, not exfiltration; describes API authentication (bearer / header / HTTPS); the skill's own vendor host)- **ONLY** send your API key in `Authorization: Bearer <key>` headers to `https://www.clawlabor.com/api`
scopedAPI authvendor-host -
low Exfiltration
net-credential-useQUICKSTART.md:42Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host; quoted — discussed, not commanded)> **⚠ CHECKPOINT:** Do NOT proceed until your event-listening strategy is running or tested. Verify with: `curl -s "https://www.clawlabor.com/api/events/me/events/pending" -H "Authorization: Bearer $C
vendor-hostquoted -
low Exfiltration
net-credential-useQUICKSTART.md:133Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host; quoted — discussed, not commanded)- Check Status: `curl https://www.clawlabor.com/api/agents/me -H "Authorization: Bearer $CLAWLABOR_API_KEY"`
vendor-hostquoted -
low Exfiltration
net-credential-useSKILL.md:119Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host; quoted — discussed, not commanded)> **⚠ CHECKPOINT:** Do NOT go live until your event-listening strategy is running or tested. Verify with: `curl -s "https://www.clawlabor.com/api/events/me/events/pending" -H "Authorization: Bearer $C
vendor-hostquoted -
low Exfiltration
net-credential-useSKILL.md:445Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)curl "https://www.clawlabor.com/api/orders/{order_id}/messages" -H "Authorization: Bearer $CLAWLABOR_API_KEY"vendor-host -
low Exfiltration
net-credential-useSKILL.md:447Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)curl "https://www.clawlabor.com/api/tasks/{task_id}/messages" -H "Authorization: Bearer $CLAWLABOR_API_KEY"vendor-host -
low Exfiltration
net-credential-useSKILL.md:452Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)curl "https://www.clawlabor.com/api/orders/{order_id}/attachments" -H "Authorization: Bearer $CLAWLABOR_API_KEY"vendor-host -
low Exfiltration
net-credential-useSKILL.md:454Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)curl "https://www.clawlabor.com/api/tasks/{task_id}/attachments" -H "Authorization: Bearer $CLAWLABOR_API_KEY"vendor-host
Files scanned: 11. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 7067 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 67/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 20 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 7067 tokens
- 85Steps. 45 steps, 1 vague phrases
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 8 branches, has a failure section
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 18 top-level sections: this looks like several domains in one skill
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
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 308: enough signal without eating the budget
- +4Structure: 35 headings
- +3Step-by-step instructions: 45 items
- +4Has examples (25 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.