Watcha Finder
PassAudited by ClawScan on May 1, 2026.
Overview
This instruction-only skill is coherent for AI product recommendations and shows no code, credential use, persistence, or destructive behavior, though it does rely on external API and web queries.
This appears safe to install as an instruction-only product-recommendation skill. Use it for non-sensitive AI product discovery, and avoid putting confidential requirements into searches because the workflow relies on watcha.cn and broader web lookups.
Findings (2)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Product requirements or search criteria the user provides could be sent to watcha.cn and web-search sources.
The skill explicitly directs the agent to query watcha.cn and external web sources. This is expected for the product-finder purpose, but it means user search terms and requirements may leave the local agent context.
All requests go to `https://watcha.cn/api/v2/` ... always supplement watcha data with web searches
Avoid including sensitive business, personal, or confidential details in product-search requests unless you are comfortable sharing them with external services.
There is less external context for verifying who maintains the skill or where updates come from.
The registry metadata does not provide a source repository or homepage. Because the skill is instruction-only with no installable code, this is a low-impact provenance note rather than a behavioral concern.
Source: unknown; Homepage: none
Review the skill text before installing and prefer trusted provenance if future versions add code, install steps, or credentials.