A cross-border-review-analysis
跨境电商评论分析 Skill：同一产品在美国、英国、德国、日本等站点的抱怨点往往不同。 本 Skill 支持八大站点采集与跨站对比，帮你判断某个市场该不该本地化改款、 文案要不要换说法。Use when the user asks about cross-border e-commerce, multi-marketplace review comparison, localization, 跨境电商、多站点分析、海外市场、 本地化、欧洲站、日本站、站点对比。Requires an ARI API key (ari_live_*).
跨境电商评论分析 Skill：同一产品在美国、英国、德国、日本等站点的抱怨点往往不同。 本 Skill 支持八大站点采集与跨站对比，帮你判断某个市场该不该本地化改款、 文案要不要换说法。Use when the user asks about cross-border e-commerce…
- Safety 60%
- Quality 40%
- Tests bonus
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
- Add evals/evals.json with 4–6 real requests and expected answers: the full check will then use your cases instead of a model draft.
- Add a spec.yaml with triggers and assertions (skilltest init): the behaviour contract for CI.
Guard findings · 1
✓ No critical or high findings
Medium and low: 1
-
medium Exfiltration
net-redirectable-api-keyscripts/ari.py:61Helper 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: 9. Evidence is masked. Grey chips explain why severity was lowered.
Lint
- note
frontmatter-keyunknown frontmatter key "display_name" - note
frontmatter-keyunknown frontmatter key "agent_created" - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "displayName" - note
frontmatter-keyunknown frontmatter key "summary"
Process maturity 45/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 6 mutating operations with no state check
- 40Consistency. Frontmatter name (cross-border-review-analysis) differs from the folder (cross-border)
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 69 steps
- 100Execution cost. Instruction body is 2366 tokens
- low 10 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
- +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
- +3Description length 269: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 69 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 1 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.