BB alibabacloud-lindorm-agent-skill
Alibaba Cloud Lindorm cloud native multi-model database Skill. Covers instance management, monitoring, performance, storage, connections, backup, migration, permissions, slow query, SQL development, search engine usage, vector retrieval, AI engine calls, multimodal image-text search, and knowledge base search. Lindorm is domain-specific knowledge — answers MUST reference Skill documents or official Alibaba Cloud documentation; direct responses from training knowledge are prohibited. Triggers: "Lindorm", "LindormTable", "LindormTSDB", "LindormSearch", "Lindorm AI", "HBase", "lindormcli", "lindorm-cli", "Lindorm CLI", "alihbase", "AliHBase", "HBase Shell", "宽表引擎", "时序引擎", "搜索引擎", "向量引擎", "向量检索", "多模态检索", "图文检索", "以图搜图", "以文搜图", "知识库检索", "RRF", "rerank", "embedding", "Lindorm instance", "Lindorm monitoring", "Lindorm connection", "Lindorm slow query", "Lindorm SQL", "Lindorm 查询", "Lindorm 执行SQL", "Lindorm 测试连接", "Lindorm backup", "Lindorm storage".
As a process B 74/100 · Nearly there — weak spots: 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 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
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 · 6
✓ No critical or high findings
Medium and low: 6
-
medium Dangerous commands
cmd-privilegereferences/03-ref/cli-installation-guide.md:33Privilege escalation / world-writable permissionssudo mv aliyun /usr/local/bin/
-
medium Dangerous commands
cmd-privilegereferences/03-ref/cli-installation-guide.md:48Privilege escalation / world-writable permissionssudo mv aliyun /usr/local/bin/
-
medium Dangerous commands
cmd-privilegereferences/03-ref/cli-installation-guide.md:61Privilege escalation / world-writable permissionssudo mv aliyun /usr/local/bin/
-
medium Dangerous commands
cmd-privilegereferences/03-ref/cli-installation-guide.md:74Privilege escalation / world-writable permissionssudo mv aliyun /usr/local/bin/
-
low Secrets in code
secret-password-literalreferences/02-ops/user-permission.md:392Hard-coded password / key literal (may be an example)ALTER USER employee_username SET PASSWORD = 'RandomStrongPassword!@#$%123456';
-
low Secrets in code
secret-password-literalreferences/02-ops/user-permission.md:493Hard-coded password / key literal (may be an example)ALTER USER existing_username SET PASSWORD = 'NewP…123!';
Files scanned: 29. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
Process rating: all ten parameters 74/100
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 4 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Failures and branches. 4 branches
- 70Execution cost. Instruction body is 4455 tokens
- 100Steps. 15 steps
- 100Result and completion. Output format and completion criterion are stated
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The skill ranks results itself: that belongs to the system behind the tool, not the model
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)
- +3Description length 959: 120–800 characters recommended
- -213 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +5Description quotes 23 example trigger phrases
- +4Structure: 20 headings
- +3Step-by-step instructions: 15 items
- +3Output format is stated explicitly
- +4Has examples (7 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.