SKILLEMALL.ai
GitHub ↗ RU Sign in

CF alibabacloud-loongcollector-ops

Alibaba Cloud LoongCollector / SLS installation, collection onboarding, Pipeline config management and validation, machine groups, permission troubleshooting, and Lens queries. HARD RULE: for matching requests, the first tool MUST load this skill before any SSH probe, directory setup, checklist/file write, or cloud read. Triggers: "安装 LoongCollector", "ECS 安装采集器", "自建 Linux 主机安装 LoongCollector", "ACK 安装 loongcollector", "自建 K8s 部署采集", "从安装到能查到日志", "SLS 日志采集接入", "SLS 日志采集接入相关的事", "修改采集配置", "改采集配置", "采集配置校验", "validate_pipeline.py", "SLS 机器组", "新建 Logtail Pipeline 采集配置", "Logtail Pipeline", "ClusterAliyunPipelineConfig", "SLS Lens 查询", "无数据排查", "心跳异常", "SLS 采集权限排查", "SLS 权限排查", "阿里云 CLI 凭证没有 SLS 操作权限", "Logtail", "iLogtail", "AgentSight", "Agentloop", "input_agentsight", "eBPF Runtime", "ebpf-event".

ClawHub Agent Skills author: alibabacloud-skills-team v0.0.2 MIT-0 50 files · 3 scripts body ≈ 15 857 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

Alibaba Cloud LoongCollector / SLS installation, collection onboarding, Pipeline config management and validation, machine groups, permission troubleshooting…

As a process F 68/100 · Will not run — References files that are not bundled: references/*

ProcedureKubernetesTerraformInfrastructuretype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
C
73/100
safety, quality, tests
Safety 60%
82
Quality 40%
60
Run on models
none yet
Process rating
F
68/100
Will not run
References files that are not bundled: references/*
Tools and files w 18
0
Result and completion w 14
40
Execution cost w 6
40
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Exfiltration medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

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.

Secrets in code medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The files contain someone else's key or token. If it is live, your agent will call third-party services under a stranger's identity; if it was revoked, the skill's scripts simply fail. Such a key often arrives with the author's whole workspace, personal data included.

For the author

The key is visible to everyone who downloaded the skill and has likely been copied by catalog-scanning bots already. Revoke it now, check bills and access logs, then reissue.

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  3. The text references files that are not there: add them or drop the references.
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 · 6

✓ No critical or high findings

Medium and low: 6
  • medium Exfiltration exfil-read-secret-files references/cli-contracts.yaml:284
    Reads credential / secret files (detector / deny-list definition)
    secret_rule: "Write config to 0600 tempfile; never print/cat kubeconfig or client certs; do not overwrite ~/.kube/config"
    detector
  • medium Dangerous commands cmd-privilege references/install-host.md:34
    Privilege escalation / world-writable permissions
    printf '<id>\n' | sudo tee /etc/ilogtail/user_defined_id >/dev/null
  • medium Secrets in code secret-private-key scripts/redact_output.py:43
    Private key material (key header without key body; quoted — discussed, not commanded)
    text, n = PRIVATE_KEY.subn("-----BEGIN PRIVATE KEY----- …", text)
    header onlyquoted
  • low Secrets in code secret-high-entropy-token references/plugin-version-gates.yaml:74
    High-entropy token-like string (may be an id, hash or a credential)
    VC-0…th:
  • low Secrets in code secret-high-entropy-token references/plugin-version-gates.yaml:81
    High-entropy token-like string (may be an id, hash or a credential)
    VC-0…ex:
  • low Dangerous commands cmd-privilege scripts/render_loongcollector_install_cmd.py:79
    Privilege escalation / world-writable permissions (string literal in code, not executed)
    "printf '%s\\n' | sudo tee /etc/ilogtail/user_defined_id >/dev/null"
    code literal

Files scanned: 50. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning body-long SKILL.md body ≈ 15857 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: references/*

Process rating: all ten parameters 68/100

Will not run. References files that are not bundled: references/*
  • 0Tools and files. 1 referenced file(s) missing: references/*
  • 40Result and completion. Does not say what the result is
  • 40Execution cost. Instruction body is 15857 tokens: crowds the task out of the window
  • 85Steps. 73 steps, 1 vague phrases
  • 100When it triggers. States when to use and when not to
  • 100Inputs and preconditions. Inputs and preconditions are listed
  • 100Failures and branches. 10 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 17 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (6 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

  • +4Description does not say when NOT to use the skill (false activations)
  • +3Description length 809: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -5TODO / placeholder text left in the skill
  • +1No license
  • +2Single-language instructions
  • +5Description quotes 26 example trigger phrases
  • +4Structure: 20 headings
  • +3Step-by-step instructions: 73 items
  • +4Has examples (5 code blocks)
  • +4Reference files are cited in the instructions (22 of 22)
  • +3All 11 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 60.

External checks

ClawHub: suspicious
This skill is coherent for Alibaba Cloud log-collector operations, but it needs Review because it can run remote installers on hosts and contains unsafe shell command construction.
LLM: suspicious (high) · 6 Sept 2026