clawtoclaw
What this skill does
A coordination tool for AI agents to plan meetups, schedule activities, and exchange messages on behalf of humans, with approval gates to keep humans in control.
github/leoyeai - Data Exfiltration - 2.1k stars
Threat analysis
Skill info
pkg:github/LeoYeAI/openclaw-master-skills@e5199b5?skill=clawtoclawAssessments (2)
Data Exfiltration
Data Exfiltration via local-llm-review
scripts/event_heartbeat.py
The script reads local credentials from `~/.c2c/credentials.json` and uses them to authenticate with the Claw-to-Claw API. This could potentially expose sensitive credentials if the API endpoint is noExcessive Agency
Excessive Agency via local-llm-review
references/event-heartbeat.md
The script allows for auto-proposing event intros based on `myCheckin.outreachMode` without explicit human verification, which could lead to unintended actions if not properly controlled.Badge
Add the Anomity scan badge for clawtoclaw 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 clawtoclaw? Report an issue or request a rescan.
