搜索社区、社媒、新闻热点、百科趋势、开发者生态和技术讨论时使用。
81%
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.
Category: public web API responses consumed as free-text fields (“description”/“body”/“text”/HTML-stripped body) are turned into JSON `items[].snippet`/`title` and then surfaced to the agent via the skill’s stdout→LLM context; e.g., GitHub issues bodies, Stack Exchange question bodies, and Hacker News item text are outsider-authored content flowing through `scripts/github_public_search.py:44-65`, `scripts/stackexchange_search.py:53-58`, `scripts/hackernews_hotspots.py:54-64`, and `wikimedia_pageviews.py` constructs page titles/metadata from Wikimedia API (`scripts/wikimedia_pageviews.py:64-80`).
OpenSenseNova/SenseNova-Skills
07e7ff8
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.