FC yutori-web-research
Use Yutori’s Research API and Browsing API (cloud browser) to research topics, collect sources, and extract structured facts from the web. Use when the user asks to “research X”, “monitor/find papers”, or “navigate to a site and extract info” and you have access to YUTORI dev/prod endpoints via YUTORI_API_BASE and an API key in env (YUTORI_API_KEY or ~/.openclaw/openclaw.json env.YUTORI_API_KEY).
As a process C 63/100 · Has gaps — weak spots: inputs and preconditions, running it twice, progress reporting
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 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
- Remove the critical guard findings (secrets, dangerous commands, hidden instructions): while they stand the skill is blocked and cannot grade above F.
- 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
-
critical Exfiltration
exfil-send-secrets-to-urlskill-card.md:24Instruction to send secrets/history to an external endpointRisk: The skill can send research prompts, browsed URLs, and the Yutori API key to the endpoint configured in YUTORI_API_BASE.
Medium and low: 1
-
medium Exfiltration
net-redirectable-api-keyscripts/yutori-research.mjs:16Helper 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
Files scanned: 3. 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 63/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 4 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (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. 21 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 783 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
- +4Description does not say when NOT to use the skill (false activations)
- -4Absolute local paths (C:\Users, /home/…): not portable
- +1No license
- +2Single-language instructions
- +5Description quotes 3 example trigger phrases
- +3Description length 399: enough signal without eating the budget
- +4Structure: 7 headings
- +3Step-by-step instructions: 21 items
- +3Output format is stated explicitly
- +4Has examples (2 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.