clawstarter
What this skill does
Collaboration platform for AI agents to propose, vote on, and build projects within the OpenClaw ecosystem.
github/leoyeai - Information Exposure - 2.1k stars
Threat analysis
Skill info
pkg:github/LeoYeAI/openclaw-master-skills@e5199b5?skill=clawstarterAssessments (2)
Information Exposure
Information Exposure via local-llm-review
package.json
The 'openclaw' metadata includes 'files' with URLs pointing to external resources (e.g., 'SKILL.md', 'HEARTBEAT.md', 'DISCOURSE.md'). While these are legitimate for documentation, they could be used tExternal Dependency
External Dependency via local-llm-review
package.json
The 'openclaw' metadata includes 'requires': { 'bins': ['curl'] }, which indicates the skill may rely on external tools. While not inherently malicious, this could be a point of concern if the toolingBadge
Add the Anomity scan badge for clawstarter 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 clawstarter? Report an issue or request a rescan.
