AC figshare-skill
Use whenever the user wants to interact with Figshare - searching public datasets/articles, downloading Figshare files, listing their own articles/collections/projects, creating or updating articles, or uploading files (including large multi-part uploads) via the Figshare v2 REST API. Trigger on mentions of "figshare", figshare DOIs (10.6084/m9.figshare.*), figshare.com URLs, or phrases like "upload my dataset to figshare", "publish to figshare", "get figshare article".
As a process C 62/100 · Has gaps — 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
- 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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Exfiltration
net-credential-useSKILL.md:64Credential used in a network call (verify the destination is the intended service)curl -s -H "Authorization: token $FIGSHARE_TOKEN" \
Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 62/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 9 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 21 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1606 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)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +5Description quotes 4 example trigger phrases
- +3Description length 474: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 21 items
- +4Has examples (13 code blocks)
- +3All 3 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.