Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Sano Intel — 中国医疗产业情报引擎（探针资本出品）
v1.0.0探针资本出品。中国医疗产业情报引擎，覆盖10万+医疗公司、50万+融资事件、109万条专利、全市场临床试验、A/港/美三地行情。查公司/融资/临床试验/专利/赛道热度/二级市场行情。By Probe Capital. Use when user asks about Chinese healthcare/biot...
⭐ 0· 67·0 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 described capability (search companies, financing, clinical trials, patents, market data) aligns with the provided curl-based API calls. However, the skill metadata lists no required environment variables while the instructions clearly require an API token (SANO_TOKEN). Also the service endpoints are raw IP addresses (47.102.196.1) rather than an identifiable domain or homepage, which reduces provenance.
Instruction Scope
SKILL.md instructs the agent/user to export SANO_TOKEN and shows curl commands that always include X-API-Key. It also recommends writing the token into ~/.zshrc (persistent storage) and uses plain HTTP endpoints (ports 5005 and 8081). These instructions ask the user to store and transmit a sensitive secret to an IP address over insecure HTTP and therefore go beyond harmless querying guidance.
Install Mechanism
There is no install spec and no code files; this is instruction-only. That minimizes installation risk because nothing is downloaded or written by the skill itself.
Credentials
Although the skill metadata declares no required env vars, the runtime instructions explicitly require SANO_TOKEN (an API secret). This mismatch is misleading. The instructions also encourage persisting the token in shell startup files, increasing the risk of accidental leak. The token requirement is proportionate to calling an API, but the lack of declaration and guidance to persist it are problematic.
Persistence & Privilege
The skill does not request persistent platform privileges (always:false) and contains no install step. However, it advises users to persist their API token in ~/.zshrc, which creates long-lived credentials on the host; that persistence is user-directed rather than a platform-level permission, but still a risk the user should consider.
What to consider before installing
Proceed with caution. The skill asks you to obtain and export an API token (SANO_TOKEN) but the metadata does not declare this requirement—ask the publisher for a trusted homepage and documentation before providing secrets. Avoid writing tokens to ~/.zshrc or other persistent files; prefer ephemeral environment variables or a credential manager. Verify the API endpoints (the SKILL.md uses raw IP 47.102.196.1 and plain HTTP on nonstandard ports); demand HTTPS and a verifiable domain or certificate to avoid man-in-the-middle risk. If you must test it, create a limited-scope or revocable token, monitor usage, and rotate/delete the token afterward. If the provider cannot supply a reputable domain, privacy policy, or published source, consider not installing/using the skill.Like a lobster shell, security has layers — review code before you run it.
latestvk972vfv9rp4nahyaw58wh2d4h583tbjs
License
MIT-0
Free to use, modify, and redistribute. No attribution required.