News Fetcher (by luogao)
Analysis
This skill appears purpose-aligned for fetching public news and archives, with documented external service use and a small local preference file.
Findings (3)
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.
Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.
const TAVILY_API_KEY = process.env.TAVILY_API_KEY; ... 'Authorization': `Bearer ${TAVILY_API_KEY}`The script uses an optional Tavily credential to authenticate to Tavily's search API, which is expected for the advertised alternative-source search feature.
Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.
archive.today / Wayback Machine ... 使用 Tavily API 搜索同一事件的免费报道
The skill intentionally sends article URLs or search queries to third-party archive/search services as part of its core workflow.
检查配置文件 `CONFIG/news-preferences.md` ... 保存偏好 → 写入 `CONFIG/news-preferences.md`
The skill persists user news preferences in a workspace file and reads them later to guide news selection.
