Use when researching China market, industry, macro, trade, procurement, listed-company disclosure, regulation, IP, healthcare, logistics, energy, environment, or industrial-operation information using free official sources with no registration, no API key, and no cryptocurrency data.
91%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
SKILL.md workflow step 2/3 requires using browser-use to open CNINFO/other official webpages and publicly downloadable documents, so at runtime the LLM likely ingests outsider-authored free text from those fetched pages/PDFs (and possibly other sites) into its context for extraction/summarization.
OpenSenseNova/SenseNova-Skills
004a242
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.