Skills/ClawHub/yotta-present

yotta-present@0.3.0

VERIFIED· install only

Publisher claims: "元呈 —— AI 输出的默认呈现层：智能体先把输出内容判为「内容类型」，再选「呈现形态」（结论卡/表格/正文/指标板/问答卡/报告/图表…），用 yotta_present CLI 或 present_result MCP 统一渲染成可复制的 Markdown / 纯文本（按需附本地 SVG）。平台自适应（--platform / platform）：webchat 完整 Markdown、discord/whatsapp 表格转列表+标题转加粗、plain 去符号；渲染通道（--channel / channel）：auto 按 platform 映射 plain→r0 去 emoji、其余→r1 emoji 徽章+引用条（r0 保底无色 / r1 增强，r2/r3 高级美化未开放）；命名场景模板（vuln_report/faq/status，references/templates.json 可热更新）一次定义多处复用；codeblock + bold_keys 加粗 + max_len 长度熔断。触发：默认——凡交付给用户的 AI 输出都经元呈（判型 → 选形态 → 渲染）呈现；例外见正文白名单。边界：不做交互式图表编辑器 / BI / 数据分析工具；图表只是呈现形态之一；不做内容改写 / 判断本身。AI 首次使用自动接入 yotta-present MCP（写 mcpServers + 永久记忆护栏，均需用户明确同意），输出默认统一呈现、未加载时降级 CLI。" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher gon-kvs · publishing for 72 daysInstalls 422Last detonated 7d ago
$clawhub install yotta-present
WatchReport an issue

Coverage

Install scripts ran; no agent task scenario for this bundle.
Tested
install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; install scripts ran; no agent task scenario for this bundle) on 2026-11-07 and scored it 87/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessexec /usr/bin/dirname
0.0sprocessexec /usr/bin/uname
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocesssecond launch, clock +45 days, CI unset
0.1sprocessexec /usr/bin/faketime
0.1sprocessexec /usr/bin/dirname
0.1sprocessexec /usr/bin/uname

Static findings

MEDIUM
npx invocation of non-well-known packageSKILL.md:196 · npx invocation of non-well-known package — may execute untrusted code4. **未安装** → 提示用户：这是可选增强，如需去味可安装，命令：`npx -y @yottameta/yotta-humanize --agent <agent-name>`（或见其 README 的 git clone / ZIP / install.sh）；**不要替用户强制安装，不要默认它已存在**；用户装好后 AI 再使用。Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Python subprocess execution detectedscripts/test_yotta_present.py:304 · Python subprocess execution detectedproc = subprocess.run([py, script], input=inp, capture_output=True, text=True, encoding="utf-8", timeout=60)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Excessive HTML entities detectedscripts/test_yotta_chart.py:43 · Excessive HTML entities detected — may be obfuscating contentcheck("转义 & < >", yc._e('&<>"\'') == "&amp;&lt;&gt;&quot;&apos;")Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
npx invocation of non-well-known packagebin/install.js:8 · npx invocation of non-well-known package — may execute untrusted code* npx -y @yottameta/yotta-present # 安装到检测到的项目级目录Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Python subprocess execution detectedscripts/test_yotta_present.py:55 · Python subprocess execution detectedreturn subprocess.run([py, script] + args, input=inp, capture_output=True,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
npx invocation of non-well-known packagebin/install.js:6 · npx invocation of non-well-known package — may execute untrusted code* npx -y @yottameta/yotta-present --dir PATH # 装到指定目录（用户改了目录的智能体）Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagebin/install.js:7 · npx invocation of non-well-known package — may execute untrusted code* npx -y @yottameta/yotta-present -g # 安装到全部已知智能体用户级目录Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagebin/install.js:5 · npx invocation of non-well-known package — may execute untrusted code* npx -y @yottameta/yotta-present --agent <name> # 按智能体默认用户级目录安装（推荐）Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagebin/install.js:9 · npx invocation of non-well-known package — may execute untrusted code* npx -y @yottameta/yotta-present --list # 列出智能体 -> 默认目录Fix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈2,292 tok
1 file · 19 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

yotta-present@0.3.0 safety verdict: Verified (install only) — KillerSkills