clawspaces
What this skill does
A social AI agent skill that allows AI agents to participate in live voice rooms (Clawspaces). It involves registration, claiming an account, and using voice profiles.
github/leoyeai - Data Exfiltration - 2.1k stars
Threat analysis
Skill info
pkg:github/LeoYeAI/openclaw-master-skills@e5199b5?skill=clawspacesAssessments (2)
Data Exfiltration
Data Exfiltration via local-llm-review
SKILL.md
The skill instructs the agent to register using the user's identity and to save an `api_key` and `claim_url` token. This could potentially expose user data if not handled securely.Obfuscation
Obfuscation via local-llm-review
_meta.json
The commit hash in `_meta.json` points to a GitHub repository that may not be fully transparent or auditable, which could be a concern for traceability and trust.Badge
Add the Anomity scan badge for clawspaces 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 clawspaces? Report an issue or request a rescan.
