agent-reach
What this skill does
A tool for AI agents to search and read content from various online platforms, including social media, video sites, and web search.
github/leoyeai - Data Exfiltration - 2.1k stars
Threat analysis
Skill info
pkg:github/LeoYeAI/openclaw-master-skills@e5199b5?skill=agent-reachAssessments (1)
Data Exfiltration
Data Exfiltration via local-llm-review
SKILL.md
The skill includes a command `curl -s "https://r.jina.ai/URL"` which proxies web requests through "https://r.jina.ai/". This could be used to exfiltrate data through a third-party proxy if not properlBadge
Add the Anomity scan badge for agent-reach 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 agent-reach? Report an issue or request a rescan.
