Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
1688-ranking
v1.0.41688榜单SKILL：查询1688商品榜单列表和热搜词。 支持按类目ID查询综合榜/热卖榜/好价榜，以及获取类目维度的热搜关键词。 使用1688开放平台官方API，统一鉴权，Token全局缓存共享。
⭐ 1· 136·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
medium confidencePurpose & Capability
The code files implement exactly the described functionality (ranking, keywords, category lookup) and correctly request ALI1688_APP_KEY/ALI1688_APP_SECRET/ALI1688_REFRESH_TOKEN (and optionally ALI1688_ACCESS_TOKEN). However the registry metadata at the top of the package summary claims no required env vars or primary credential while SKILL.md and the scripts do require credentials — this packaging inconsistency is unexpected.
Instruction Scope
The SKILL.md and scripts confine actions to 1688 API calls and local token caching. They do not attempt to read unrelated system files or exfiltrate data to third‑party endpoints. One scope-related behavior: the skill will auto-query and enumerate all top-level categories if the user doesn't provide a category ID, which may produce large outputs but is within the stated purpose. The SKILL.md and scripts also claim a shared token cache for all '1688' skills.
Install Mechanism
There is no installer or network download; the package is delivered as code files. No external install URLs, package managers, or archive extraction are used. This is lower risk from an install-mechanism perspective.
Credentials
Requested environment variables (AppKey, AppSecret, RefreshToken/AccessToken) are appropriate for calling the 1688 API. However the top-level registry metadata incorrectly lists no required env vars/primary credential while SKILL.md lists them as required/primary—this mismatch could mislead users and automated gating. Also the skill stores tokens persistently and shares them across other '1688' skills via a global cache, which increases the blast radius of any other skill that also uses that path.
Persistence & Privilege
The skill writes a persistent token cache file to the user's home under a .openclaw workspace path (TOKEN_CACHE_PATH). That behavior is plausible for token caching but it is persistent and shared across '1688' skills. The package does not request always:true nor modify other skills' configs, but the shared cache is a point to consider.
What to consider before installing
This skill appears to implement the claimed 1688 ranking and keyword queries and requires your 1688 AppKey/AppSecret and a refresh token (or access token). Before installing: (1) confirm the registry metadata mismatch — the package WILL need your ALI1688_APP_KEY and ALI1688_APP_SECRET even though the top-level manifest omitted them; (2) only provide credentials for a 1688 account you trust and rotate them if you stop using the skill; (3) note the skill caches tokens persistently at a shared path in your home directory (~/.openclaw/workspace/skills/.1688_token_cache.json) which is reused by other 1688 skills — consider restricting permissions or using an isolated environment if you want to avoid cross-skill sharing; (4) if you rely on the reference docs, be aware of minor inconsistencies (e.g., references/api.md describes MD5-style signing while the code uses HMAC-SHA1); (5) if you need higher assurance, review the included scripts (auth.py, ranking.py, category.py) yourself or run the skill in a sandboxed container. If you accept those trade-offs the behavior is coherent with its stated purpose; otherwise treat it as risky.Like a lobster shell, security has layers — review code before you run it.
latestvk9732bh4dvr1366fe7x85ty3qs83e8d2
License
MIT-0
Free to use, modify, and redistribute. No attribution required.