BF alibabacloud-flink-workspace-ops
Use when user explicitly asks Flink/Ververica/Realtime Compute Console workspace operations: 草稿(draft), SQL校验/执行, 部署(deployment), 作业(job), Session Cluster, namespace, 表(table), 成员(member), 变量(variable), 或 checkpoint timeout 诊断, especially with workspace/deployment/job IDs (w-*, d-*, j-*, sc-*, draft-*). Also use when prompt asks to test/verify Flink Console lifecycle flow, safety guardrails, or parameter validation for these operations. This includes prompts such as create draft, deploy draft, list deployments, start/stop job, create/list session cluster, get tables, list variables. Also use when prompt explicitly asks to run `python scripts/flink_ververica_ops.py` for Flink Console workspace operations. Do not trigger for unrelated "workspace" contexts or generic cloud/platform tasks (ECS, OSS, RDS, Kafka, Spark, Kubernetes, billing, weather). Do not trigger for Flink instance lifecycle operations (create/scale/delete/renew); those belong to alibabacloud-flink-instance-manage.
As a process F 43/100 · Will not run — References files that are not bundled: references/playbooks/*.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 · 8
✓ No critical or high findings
Medium and low: 8
-
medium Dangerous commands
cmd-pipe-to-shellreferences/cli-installation-guide.md:40Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill)curl -fsSL https://aliyuncli.alicdn.com/install.sh | bash
security skill -
low Dangerous commands
cmd-shell-rcreferences/cli-installation-guide.md:56Writes to a shell startup file (documentation of a security skill)echo 'export ALIBABA_CLOUD_ACCESS_KEY_ID=your_access_key_id' >> ~/.bashrc
security skill -
low Dangerous commands
cmd-shell-rcreferences/cli-installation-guide.md:57Writes to a shell startup file (documentation of a security skill)echo 'export ALIBABA_CLOUD_ACCESS_KEY_SECRET=your_access_key_secret' >> ~/.bashrc
security skill -
low Secrets in code
secret-high-entropy-tokenscripts/w5_workspace_admin.py:231High-entropy token-like string (may be an id, hash or a credential)from alib…els import Crea…ers, Crea…est, Resource
-
low Secrets in code
secret-high-entropy-tokenscripts/w5_workspace_admin.py:241High-entropy token-like string (may be an id, hash or a credential)headers = Crea…ers(workspace=args.workspace)
-
low Secrets in code
secret-high-entropy-tokenscripts/w5_workspace_admin.py:242High-entropy token-like string (may be an id, hash or a credential)req = Crea…est(body=body, deployment_target_name=target_name)
-
low Secrets in code
secret-high-entropy-tokenscripts/w5_workspace_admin.py:259High-entropy token-like string (may be an id, hash or a credential)from alib…els import Upda…ers, Upda…est, Resource
-
low Secrets in code
secret-high-entropy-tokenscripts/w5_workspace_admin.py:267High-entropy token-like string (may be an id, hash or a credential)headers = Upda…ers(workspace=args.workspace)
Files scanned: 25. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: references/playbooks/*.md
Process rating: all ten parameters 43/100
- 0Tools and files. 1 referenced file(s) missing: references/playbooks/*.md
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 65 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 70Failures and branches. 13 branches
- 70Execution cost. Instruction body is 4477 tokens
- 100Steps. 94 steps
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (20 tags): a typed call is more reliable
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)
- +3Description length 992: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -37 of 9 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +4Structure: 22 headings
- +3Step-by-step instructions: 94 items
- +4Has examples (6 code blocks)
- +4Reference files are cited in the instructions (9 of 10)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.