SKILLEMALL.ai
GitHub ↗ RU Sign in

CC ai-weekly

把「本周 AI 行业动态」做成一个可搜索、可筛选、支持暗色模式的单文件 HTML 周报。 用户用日常说法就能触发，例如「这周 AI 有什么大事」「给我看个 AI 简报」「做个 AI 周报」。 数据来自 14 个公开 RSS 源（国内 7 + 国外 7，国内优先），默认不调用任何付费或商业 API。 适合：AI 周报 / AI 新闻汇总 / AI 行业动态速览 / 模型排行榜与市场融资数据整理。 不适合以下情形，请勿触发： - 用户要的是「即时单条新闻」或「回答一个 AI 领域问题」，而非一份成体系的周报/简报； - 用户指定了非AI 主题（时政、体育、财经等）； - 用户只想要纯文本对话输出——此时直接在对话里回答，不要生成 HTML； - 用户要求部署、推送、改仓库设置等运维动作（见正文「能力边界」，这些不属本技能触发能力）。 典型触发：这周 AI 有什么大事。 典型不触发：帮我看下今天沪深300 多少点。 能力边界（重要）：本技能默认行为只是生成新闻内容——抓取、生成 HTML、校验、展示。 它不会部署、不会推送飞书、不会改动仓库任何设置（含 GitHub Pages）、不会执行 git push。 部署/推送/切 Pages 源/刷新排行榜均不属于触发能力，仅在用户明确点名要求时才执行。

ClawHub Claude Code author: Elisabeth15501 v4.1.4 MIT-0 80 files · 36 scripts body ≈ 1 258 tokens Open the sourceclawhub.ai↗ analyzed 7 d ago

把「本周 AI 行业动态」做成一个可搜索、可筛选、支持暗色模式的单文件 HTML 周报。 用户用日常说法就能触发，例如「这周 AI 有什么大事」「给我看个 AI 简报」「做个 AI 周报」。 数据来自 14 个公开 RSS 源（国内 7 + 国外 7，国内优先），默认不调用任何付费或商业 API。 适合：AI 周报…

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

IntegrationGitHubAI and agentstype 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
78/100
safety, quality, tests
Safety 60%
84
Quality 40%
70
Run on models
none yet
Process rating
C
51/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
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.

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. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
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 net-redirectable-api-key scripts/deploy.py:104
    Helper sends the API key to a host configured by an environment variable — the key can be redirected to another server
    API key + configurable base URL from environment
  • medium Broad scope meta-broad-allowed-tools SKILL.md:1
    Broad tool permissions pre-approved: Bash
    allowed-tools: Bash Read Write Glob Grep WebSearch WebFetch
  • low Secrets in code secret-high-entropy-token model_profiles_unverified.json:183
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "Link…32B": {
    quoted
  • low Secrets in code secret-high-entropy-token model_profiles_unverified.json:184
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "name": "Link…32B",
    quoted
  • low Secrets in code secret-high-entropy-token model_profiles.json:829
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "Link…32B": {
    quoted
  • low Secrets in code secret-high-entropy-token model_profiles.json:830
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "name": "Link…32B",
    quoted
  • low Secrets in code secret-high-entropy-token model_profiles.json:844
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "Link…32B": {
    quoted
  • low Secrets in code secret-high-entropy-token model_profiles.json:845
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "name": "Link…32B",
    quoted

Files scanned: 80. 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")
  • note frontmatter-key unknown frontmatter key "slug"
  • note frontmatter-key unknown frontmatter key "displayName"
  • note frontmatter-key unknown frontmatter key "summary"
  • note frontmatter-key unknown frontmatter key "homepage"

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
  • 0Failures and branches. Linear process with no failure handling
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 4 mutating operations with no state check
  • 100Tools and files. Tools declared in frontmatter
  • 100Steps. 38 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 1258 tokens

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)
  • +3Output format is not stated: the model decides each time
  • -37 of 10 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +3Description length 555: enough signal without eating the budget
  • +4Structure: 13 headings
  • +3Step-by-step instructions: 38 items
  • +4Has examples (1 code blocks)
  • +4Reference files are cited in the instructions (2 of 4)

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

External checks

ClawHub: suspicious
The skill mostly matches an AI weekly report generator, but it also includes persistent scheduler and deployment paths that can push public updates using local credentials with weaker disclosure than the main skill text suggests.
LLM: suspicious (high) · 11 Oct 2026