elsewhere-news
What this skill does
A news and content browsing skill for Elsewhere, a media platform focusing on China's tech and startup ecosystem. It allows users to browse articles and podcasts, and includes a recommendation system
github/leoyeai - Data Exfiltration - 2.1k stars
Threat analysis
Skill info
pkg:github/LeoYeAI/openclaw-master-skills@e5199b5?skill=elsewhere-newsAssessments (3)
Data Exfiltration
Data Exfiltration via local-llm-review
SKILL.md
The skill instructs users to execute commands that fetch data from external URLs (e.g., `curl -s https://raw.githubusercontent.com/PitayaK/elsewhere-news/main/SKILL.md`). This could be used to exfiltrRemote Code Execution
Remote Code Execution via local-llm-review
SKILL.md
The skill provides instructions for users to execute arbitrary shell commands (e.g., `curl -s https://raw.githubusercontent.com/PitayaK/elsewhere-news/main/SKILL.md | head -5`). This could be exploiteConfiguration Dependency
Configuration Dependency via local-llm-review
SKILL.md
The skill relies on the existence of a `TASTE.md` file, which is not provided by the skill itself. This could be a potential point of failure or manipulation if the file is not properly managed.Badge
Add the Anomity scan badge for elsewhere-news to your README.
How Anomity governs this at runtime
Scan-time vetting tells you what a skill says it will do. Anomity's Endpoint Sensor sees what agents actually do: it discovers skills alongside every other AI artifact on the endpoint, and runtime governance can allow, deny, or log the tool calls a skill triggers. Policy violations route to your SIEM, Slack, email, or Jira, backed by a queryable 90-day audit trail.
Book a 30-minute demo to see your own skill inventory.
Methodology and disputes
Every skill is assessed by the Anomity Skill Intelligence engine against its public source; findings indicate risk patterns, not confirmed exploitation. Maintainer of elsewhere-news? Report an issue or request a rescan.
