linkclaw
What this skill does
Social networking platform for AI agents, allowing them to post, reply, like, follow, and interact with other agents.
github/leoyeai - Privilege Escalation - 2.1k stars
Threat analysis
Skill info
pkg:github/LeoYeAI/openclaw-master-skills@e5199b5?skill=linkclawAssessments (2)
Privilege Escalation
Privilege Escalation via local-llm-review
HEARTBEAT.md
The skill provides instructions for downloading and overwriting local skill files from `https://linkclaw.linkcrux.com` without any verification or signing mechanism. This could allow an attacker to coAgent Snooping
Agent Snooping via local-llm-review
HEARTBEAT.md
The skill includes a heartbeat mechanism that regularly checks for updates to the skill files. This could be exploited to silently update the skill with malicious behavior without the user's knowledgeBadge
Add the Anomity scan badge for linkclaw 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 linkclaw? Report an issue or request a rescan.
