tiktok-demand-mining@1.1.2
VERIFIED· install onlyPublisher claims: "获取成千上万条TikTok社媒平台的实时用户评论内容做聚类与情感分析,抽取高频痛点、功能诉求与未被满足的需求,把用户评论变成“用户到底要什么”的结构清单,按痛点聚类、标注频次与情感强度,直接喂给选品与产品工程,输出需求机会清单与佐证原文。提供3个能力①关键词搜索(可按点赞/相关度排序、发布时间筛选)②博主作品获取,按主页链接或用户名批量获取公开作品列表,支持最新/最热排序 ③视频评论抓取,按视频链接或作品 ID 获取评论内容、评论者与互动数据,输出结构化 JSON(含作者、互动数据、标签、链接)。" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Bundled scripts ran with no arguments; no agent task scenario for this bundle.- Tested
- 8 of 20 bundled scripts run with no arguments (the rest were not run: per-bundle cap), 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 1.1.1
vet-skills diff tiktok-demand-mining 1.1.1 1.1.2In the sandbox, this version reached for nothing 1.1.1 did not. Compared from the two recorded runs, not from source.
1.1.1 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 2026-11-22 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 · 1 s · 2 scenarios · 0 deviationsStatic findings
<summary><b>Q:运行报错,提示无权限 / 退出码 3?</b></summary> A:环境变量未配置或 Token 格式不对(需 16–256 位,仅字母、数字、下划线、连字符)。 ```bash # Windows set GUAIKEI_API_TOKEN=你的TOKEN # macOS / LinuFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.<summary><b>Q:会不会泄露我的 Token?</b></summary> A:Token 只从环境变量读取,不会出现在 stdout、日志文件或错误信息中。调用时会随请求头发送到数据服务 `www.guaikei.com`(这是数据获取的必要环节)。Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.<summary><b>Q:报错 `PLAN_LIMIT` / 提示包月受限?</b></summary> A:技能侧硬上限仍是 10000 条/次(按量 Token)。**包月 Token** 搜索/作品最多 30、评论最多 40,超限返回 `PLAN_LIMIT`(退出码 1),不要当网络错误同参重试。可降 `--Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.Cost to the agent
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.