CB alibabacloud-tair-devtoolset
Alibaba Cloud Tair development toolkit — 7 capabilities covering architecture selection, data structure design, instance creation & configuration, connection management, performance monitoring, error troubleshooting, and backup & recovery. Executes real cloud operations via aliyun CLI (creating instances, modifying whitelists, managing backups, restoring data). Restore operations are high-risk and will overwrite current data. Ensure the RAM account has required permissions (see references/ram-policies.md). Triggers: "tair", "create tair instance", "tair instance", "redis", "data structure", "backup", "PITR", "tair architecture", "tair connection", "tair error".
As a process B 70/100 · Nearly there — weak spots: result and completion, when it triggers
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 SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 13
✓ No critical or high findings
Medium and low: 13
-
medium Dangerous commands
cmd-privilegereferences/cli-installation-guide.md:30Privilege escalation / world-writable permissionssudo mv aliyun /usr/local/bin/
-
medium Dangerous commands
cmd-privilegereferences/cli-installation-guide.md:45Privilege escalation / world-writable permissionssudo mv aliyun /usr/local/bin/
-
medium Dangerous commands
cmd-privilegereferences/cli-installation-guide.md:58Privilege escalation / world-writable permissionssudo mv aliyun /usr/local/bin/
-
medium Dangerous commands
cmd-privilegereferences/cli-installation-guide.md:71Privilege escalation / world-writable permissionssudo mv aliyun /usr/local/bin/
-
medium Dangerous commands
cmd-privilegereferences/instance-creation/connect-create-instance.md:19Privilege escalation / world-writable permissionssudo mv aliyun /usr/local/bin/
-
medium Dangerous commands
cmd-privilegereferences/instance-creation/connect-create-instance.md:24Privilege escalation / world-writable permissionssudo mv aliyun /usr/local/bin/
-
low Secrets in code
secret-high-entropy-tokenreferences/connection-management/connect-cluster.md:168High-entropy token-like string (may be an id, hash or a credential)template.setValueSerializer(new Gene…zer());
-
low Secrets in code
secret-password-literalreferences/connection-management/connect-standalone-or-proxy.md:37Hard-coded password / key literal (may be an example)String password = "r-bp…3p1****:Dat…123";
-
low Secrets in code
secret-high-entropy-tokenreferences/connection-management/connect-standalone-or-proxy.md:182High-entropy token-like string (may be an id, hash or a credential)template.setValueSerializer(new Gene…zer());
-
low Secrets in code
secret-password-literalreferences/connection-management/connect-with-tls.md:84Hard-coded password / key literal (may be an example)password="redistest:Pas***23",
-
low Secrets in code
secret-password-literalreferences/connection-management/connect-with-tls.md:102Hard-coded password / key literal (may be an example)password="redi…234",
-
low Secrets in code
secret-password-literalreferences/connection-management/connect-with-tls.md:164Hard-coded password / key literal (may be an example)Password = "redistest:Pas***23",
-
low Secrets in code
secret-password-literalreferences/connection-management/connect-with-tls.md:283Hard-coded password / key literal (may be an example)Password: "redistest:Pas***23",
Files scanned: 18. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5848 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 70/100
- 20When it triggers. No condition that starts the skill
- 40Result and completion. Does not say what the result is
- 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 5848 tokens
- 100Steps. 58 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 7 example trigger phrases
- +3Description length 669: enough signal without eating the budget
- +4Structure: 44 headings
- +3Step-by-step instructions: 58 items
- +4Has examples (13 code blocks)
- +4Reference files are cited in the instructions (5 of 5)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.