Skills/ClawHub/idea-doctor

idea-doctor@0.3.2

VERIFIED· install only

Publisher claims: "创业点子评估、副业可行性验证:八步规则引擎做体检,Go/Pivot/Kill判定与三情景经济账报告" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher linkkhub-pixiu · publishing for 14 daysInstalls 288Last detonated 9 h ago
$clawhub install idea-doctor
WatchReport an issue

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
1 of 1 bundled script run with no arguments, with decoy credentials in the environment · every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

What changed since 0.2.5

vet-skills diff idea-doctor 0.2.5 0.3.2

In the sandbox, this version reached for nothing 0.2.5 did not. Compared from the two recorded runs, not from source.

0.2.5 was not run in the sandbox (static only); the comparison covers what static analysis recorded only.

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-19 and scored it 88/100 (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
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments
0.1sprocessexited 2: {"ok":false,"code":2,"msg":"MISSING_INPUT","hint":"用法:--in my_questionnaire.json"}
0.1sprocess1 of 1 bundled script run with no arguments
0.1sprocessscript backend runs setup only
0.1sprocessscript backend runs setup only
0.1sprocessno install scripts to re-run

Static findings

MEDIUM
File type combined with upload actionscripts/questionnaire.json:2 · File type combined with upload action — agent may exfiltrate local data files{ "_desc": "商业点子体检官问卷模板(壳包 v0.2.4)。复制本文件为 my_questionnaire.json 后填 _input;ideas 数组 1-10 条:1 条 ¥4.9,2-10 条 ¥9.9,>10 拒单(服务端 400 BATCH_TOO_LARGE:一次最多 10 个点子…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
URL with suspicious TLDSKILL.md:36 · URL with suspicious TLD — commonly used for phishing/malware提交脚本只访问唯一端点 https://linkkhub.top/idea/generate;自动预备(第 0.5 步)阶段的联网搜索是用户侧智能体在用户授权下的本机行为,非本技能脚本发起;页面、账单与该端点之外无任何外呼。Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
URL with suspicious TLDSKILL.md:35 · URL with suspicious TLD — commonly used for phishing/malware…→ 智能体必须向用户确认「付好了吗」,等用户明确回答付好了 → 智能体调用服务器订单状态查询接口(以订单号为键,返回订单支付/履约状态字段;查询接口:`GET https://linkkhub.top/api/v1/order/<订单号>`(返回 order_status/fulfill_status/has_result;has_result 为 true…Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
URL with suspicious TLDSKILL.md:104 · URL with suspicious TLD — commonly used for phishing/malware未获服务器到账确认(订单状态查询接口 `GET https://linkkhub.top/api/v1/order/<订单号>` 返回到账/履约确认)前:禁止生成任何报告内容、评分卡、明细节选、示例报告或框架演示;禁止向用户建议跳过付费或「我免费给你做一份」;禁止以「用户说付了」代替接口确认。完整报告(评分卡明细、三情景算账数值、判定结论)仅由服务端引擎在服务器确认到账后产出返回。Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
URL with suspicious TLDscripts/submit_report.js:20 · URL with suspicious TLD — commonly used for phishing/malwareconst ENDPOINT = 'https://linkkhub.top/idea/generate';Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
URL with suspicious TLDscripts/submit_report.js:127 · URL with suspicious TLD — commonly used for phishing/malware// [变更记录 2026-11-12 · v0.2.0] 新基线首版;端点 https://linkkhub.top/idea/generate。Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
URL with suspicious TLDSKILL.md:14 · URL with suspicious TLD — commonly used for phishing/malwarenetwork: 端点已于 2026-11-14 对外开放(来源:发布方验证记录 2026-11-14);提交生成需访问唯一服务端点 https://linkkhub.top/idea/generate;自动预备(第 0.5 步)阶段的联网搜索是用户侧智能体在用户授权下的本机行为,非本技能脚本发起;除此之外不发起任何网络请求(自动预备节口径不变)Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
URL with suspicious TLDSKILL.md:96 · URL with suspicious TLD — commonly used for phishing/malware…成、退款规则**未实查官方文档前不对外承诺任何具体条款**(来源与检索日期须实查官方文档后补记)。 3. **端点开放口径**:生成引擎与服务层已实装,端点 `https://linkkhub.top/idea/generate` 已于 2026-11-14 对外开放(来源:发布方验证记录 2026-11-14:POST 空 body 命中 422 `INV…Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07

Cost to the agent

Instructions loaded
≈2,067 tok
1 file · 4 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.

idea-doctor@0.3.2 safety verdict: Verified (install only) — KillerSkills