SKILLEMALL.ai

CB alibabacloud-oss-manage-cron-upload

Alibaba Cloud OSS scheduled local-folder sync skill using aliyun CLI, including integrated ossutil commands for incremental upload. Use when the user wants to schedule recurring local-to-OSS uploads, validate OSS backup prerequisites, set up cron or Task Scheduler for OSS sync, or clearly separate what stays on aliyun CLI from what remains OS-local or manual. Conditional write operations: creates the target bucket (PutBucket) only when the user confirms the bucket does not exist yet; optionally deletes test objects (DeleteObject) only when the user explicitly requests cleanup after verification. Triggers: "OSS scheduled sync", "定时同步到OSS", "aliyun ossutil cp --max-age", "aliyun ossutil cp -u", "cron upload to OSS", "Task Scheduler OSS upload", "aliyun CLI OSS sync", "本地目录增量上传 OSS".

Not recommendedcritical or high security findings
ClawHub Agent Skills author: alibabacloud-skills-team v0.0.2 MIT-0 7 files body ≈ 6 035 tokens Open the sourceclawhub.ai analyzed 3 d ago

As a process B 77/100 · Nearly there — weak spots: result and completion

IntegrationInfrastructuretype and topics are labelled automatically from the skill text
JSON
Technical rating
C
66/100
safety, quality, tests
Safety 60%
55
Quality 40%
83
Run on models
none yet
Process rating
B
77/100
Nearly there
Result and completion w 14
40
Tools and files w 18
60
Inputs and preconditions w 11
70
the three weakest of ten parameters · all ten

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.

Dangerous commands
If you install

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.

For the author

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

  1. 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.
  2. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
For the model run — optional
  • 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 · 12

  • high Dangerous commands cmd-persistence SKILL.md:308
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    schtasks /Create /SC DAILY /ST 03:00 /TN "OSS Scheduled Sync" /TR "C:\tools\oss-sync-upload.bat"
Medium and low: 11
  • medium Dangerous commands cmd-privilege references/cli-installation-guide.md:30
    Privilege escalation / world-writable permissions
    sudo mv aliyun /usr/local/bin/
  • medium Dangerous commands cmd-privilege references/cli-installation-guide.md:45
    Privilege escalation / world-writable permissions
    sudo mv aliyun /usr/local/bin/
  • medium Dangerous commands cmd-privilege references/cli-installation-guide.md:58
    Privilege escalation / world-writable permissions
    sudo mv aliyun /usr/local/bin/
  • medium Dangerous commands cmd-privilege references/cli-installation-guide.md:71
    Privilege escalation / world-writable permissions
    sudo mv aliyun /usr/local/bin/
  • low Dangerous commands cmd-cron-mention references/related-apis.md:20
    Mentions editing / listing crontab (documentation table row)
    | Local OS | `crontab -l` | Verify cron registration on Linux/macOS | Validated locally |
    table
  • low Dangerous commands cmd-cron-mention references/verification-method.md:104
    Mentions editing / listing crontab
    crontab -l
  • low Dangerous commands cmd-cron-mention references/verification-method.md:151
    Mentions editing / listing crontab (quoted — discussed, not commanded)
    - `crontab -l` behavior when no user crontab exists
    quoted
  • low Dangerous commands cmd-cron-mention SKILL.md:56
    Mentions editing / listing crontab (documentation table row)
    | `cron` or `schtasks` | Yes | Local recurring execution | `crontab -l` or `schtasks /Query /TN "OSS Scheduled Sync"` |
    table
  • low Dangerous commands cmd-cron-mention SKILL.md:296
    Mentions editing / listing crontab
    crontab -e
  • low Dangerous commands cmd-cron-mention SKILL.md:348
    Mentions editing / listing crontab (detector / deny-list definition)
    6. the local scheduler entry is visible through `crontab -l` or Task Scheduler history/query, or is documented for the user when crontab is not available in the current environment.
    detector
  • low Dangerous commands cmd-cron-mention SKILL.md:355
    Mentions editing / listing crontab (quoted — discussed, not commanded)
    - remove the cron line with `crontab -e`
    quoted

Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 6035 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 77/100

  • 40Result and completion. Does not say what the result is
  • 60Tools and files. Uses tools (bash) that frontmatter does not declare
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 70Execution cost. Instruction body is 6035 tokens
  • 85Steps. 47 steps, 1 vague phrases
  • 100When it triggers. States when to use and when not to
  • 100Failures and branches. 15 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 12 top-level sections: this looks like several domains in one skill
  • high The skill tells the model to perform an irreversible action with no human approval

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 8 example trigger phrases
  • +3Description length 791: enough signal without eating the budget
  • +4Structure: 20 headings
  • +3Step-by-step instructions: 47 items
  • +4Has examples (17 code blocks)
  • +4Reference files are cited in the instructions (5 of 5)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.

External checks

ClawHub: suspicious
This skill has a real OSS backup purpose, but it needs Review because it can set up recurring cloud uploads and includes under-scoped test-file and credential-setup guidance.
LLM: suspicious (high) · VirusTotal: · 29 May 2026