SKILLEMALL.ai
GitHub ↗ RU Sign in

BC skill-publisher

技能发布 — 将已有 Skill 三平台同步推送到 GitHub + ClawHub + SkillHub。当用户说 技能发布到三平台/发布技能更新/迭代技能发布 时触发。⚠️ 本技能的行为范围（用户须知）：① 推送代码到外部平台（GitHub/ClawHub/SkillHub），操作对外可见且可能不可逆 ② 同步到本地 TRAE 安装目录（会覆盖已有版本） ③ 在本地 docs/knowledge/ 追加发布日志。执行前会向用户确认。含安全审查、隐私清洗、版本号查重、仓库结构生成、ClawHub 自动文件排除、SkillHub dry-run 预检。Do NOT use for creating skill content, general coding, or non-skill projects.

ClawHub Agent Skills author: AI花生 v5.22.1 MIT-0 9 files body ≈ 10 460 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

技能发布 — 将已有 Skill 三平台同步推送到 GitHub + ClawHub + SkillHub。当用户说 技能发布到三平台/发布技能更新/迭代技能发布 时触发。⚠️ 本技能的行为范围（用户须知）：① 推送代码到外部平台（GitHub/ClawHub/SkillHub），操作对外可见且可能不可逆 ②…

As a process C 51/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency

IntegrationGitHubAI and agentsSoftware developmenttype 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
B
75/100
safety, quality, tests
Safety 60%
76
Quality 40%
74
Run on models
none yet
Process rating
C
51/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Running it twice w 4
30
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.

Broad scope 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 asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

How to improve

  1. 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 · 8

✓ No critical or high findings

Medium and low: 8
  • medium Exfiltration exfil-read-secret-files references/publishing-guide.md:569
    Reads credential / secret files (documentation table row)
    | Reading sensitive dirs | `cat ~/.ssh/id_rsa` | Remove |
    table
  • medium Dangerous commands cmd-pipe-to-shell references/skillhub-publishing.md:26
    Downloads and executes remote code from an unrecognised host (pipe to shell) (the skill's own vendor host)
    curl -fsSL https://skillhub.cn/install/install.sh | bash -s -- --cli-only
    vendor-host
  • medium Dangerous commands cmd-shell-rc references/skillhub-publishing.md:27
    Writes to a shell startup file
    echo 'export PATH="$HOME/.local/bin:$PATH"' >> ~/.zshrc
  • medium Broad scope meta-broad-allowed-tools SKILL.md:1
    Broad tool permissions pre-approved: Bash(rm:*)
    allowed-tools: Bash(git:*) Bash(clawhub:*) Bash(skillhub:*) Bash(gh:*) Bash(python:*) Bash(cat:*) Bash(ls:*) Bash(mkdir:*) Bash(cp:*) Bash(mv:*) Bash(rm:*) Bash(Compress-Archive:*) Read Write Edit Glo
  • low Exfiltration exfil-read-secret-files references/security-audit.md:84
    Reads credential / secret files (documentation table row; documentation of a security skill)
    | Reading sensitive dirs | `cat ~/.ssh/id_rsa` | Remove |
    tablesecurity skill
  • low Exfiltration net-credential-use references/skillhub-publishing.md:63
    Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host; quoted — discussed, not commanded)
    skillhub login --key "$SKILLHUB_TOKEN" --host https://api.skillhub.cn
    vendor-hostquoted
  • low Exfiltration net-credential-use references/skillhub-publishing.md:67
    Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)
    python "$env:USERPROFILE\.skillhub\skills_store_cli.py" login --key $token --host https://api.skillhub.cn
    vendor-host
  • low Exfiltration net-credential-use references/skillhub-publishing.md:265
    Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)
    python script.py login --key $token --host https://api.skillhub.cn
    vendor-host

Files scanned: 9. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 10460 tokens (recommended < 5000); move details to references/
  • note frontmatter-key unknown frontmatter key "slug"
  • note frontmatter-key unknown frontmatter key "displayName"
  • note frontmatter-key unknown frontmatter key "summary"

Process rating: all ten parameters 51/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 30Running it twice. 65 mutating operations with no state check
  • 40Consistency. Frontmatter name (skill-publisher) differs from the folder (skill-publisher-ai)
  • 40Execution cost. Instruction body is 10460 tokens: crowds the task out of the window
  • 50When it triggers. No condition that starts the skill
  • 50Failures and branches. 0 branches, has a failure section
  • 85Steps. 67 steps, 1 vague phrases
  • 100Tools and files. Tools declared in frontmatter
  • 100Progress reporting. Reports progress
  • low The response is described with custom markup (38 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

  • +5Description has no quoted example phrases that should trigger the skill
  • +3Output format is not stated: the model decides each time
  • -4Absolute local paths (C:\Users, /home/…): not portable
  • -276 emoji in the instructions: noise for the model
  • +2Single-language instructions
  • +4Description says when NOT to use the skill
  • +3Description length 356: enough signal without eating the budget
  • +4Structure: 32 headings
  • +3Step-by-step instructions: 67 items
  • +4Has examples (12 code blocks)
  • +4Reference files are cited in the instructions (7 of 7)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.

External checks

ClawHub: clean
This skill performs high-impact publishing actions, but its access and side effects are clearly disclosed, user-directed, and aligned with its publishing purpose.
LLM: benign (high) · VirusTotal: · 31 Jul 2026