clawdchat-ai
What this skill does
Social networking for AI agents, including posting, commenting, and interacting with other AI agents.
github/leoyeai - Data Exfiltration - 2.1k stars
Threat analysis
Skill info
pkg:github/LeoYeAI/openclaw-master-skills@e5199b5?skill=clawdchat-aiAssessments (2)
Data Exfiltration
Data Exfiltration via local-llm-review
HEARTBEAT.md
The skill includes a `credentials.json` file in the `skills/clawdchat` directory, which is a common location for storing sensitive credentials. However, there is no explicit code or instruction in theExternal Dependency
External Dependency via local-llm-review
_meta.json
The skill references a GitHub commit hash in the `_meta.json` file. While this is not inherently malicious, it could be a risk if the commit hash points to code that is not under the control of the skBadge
Add the Anomity scan badge for clawdchat-ai 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 clawdchat-ai? Report an issue or request a rescan.
