AF alibabacloud-dataworks-metadata
DataWorks metadata Skill for Alibaba Cloud — browse Data Map metadata and perform non-destructive writes via Aliyun CLI. READ scope: list/get catalogs, databases, tables, columns, partitions; query data lineage (upstream/downstream impact); list/get datasets & versions; list/get metadata collections (Category/Album) and entities inside them; preview dataset version content. WRITE scope (non-destructive only): update table & column business metadata; register lineage relationships; create/update datasets and versions; create/update metadata collections and add entities to them. This Skill exposes NO delete or remove APIs — every `delete-*` and `remove-*` operation is intentionally out of scope. For deletions, use the DataWorks console. Triggers: "dataworks metadata", "data map", "data lineage", "meta collection", "dataset", "catalog", "table info", "column info", "partition", "impact analysis", "register lineage", "create dataset", "update business metadata".
As a process F 57/100 · Will not run — References files that are not bundled: references/cli-installation-guide.md
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 skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
How to improve
- 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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Dangerous commands
cmd-pipe-to-shellSKILL.md:19Downloads and executes remote code from an unrecognised host (pipe to shell) (quoted — discussed, not commanded)> **[FORBIDDEN] Do NOT pipe a remote installer script directly into a shell** — never run anything of the form `curl ... | bash` / `curl ... | sh` / `wget ... | bash`. Piping unverified network conten
quoted
Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: references/cli-installation-guide.md
Process rating: all ten parameters 57/100
- 0Tools and files. 1 referenced file(s) missing: references/cli-installation-guide.md
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 17 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 100Steps. 6 steps
- 100Inputs and preconditions. Inputs and preconditions are listed
- 100Failures and branches. 8 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3979 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- +3Description length 972: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 13 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 11 headings
- +3Step-by-step instructions: 6 items
- +4Has examples (9 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.