Skill scan report

video-call-agent

View on GitHub

14 Low This skill sends sensitive values to an external host. Automated analysis flagged 1 additional risk pattern.

What this skill does

The skill is a video call agent that uses the Runway Characters API to start a real-time AI avatar video call. It sends a call invite link to the user and handles the call, transcript, and avatar mana

github/leoyeai - Data Exfiltration Risk - 2.1k stars

ThreatsData Exfiltration Risk Third-Party Dependency Risk

Threat analysis

Data Exfiltration Risk1 finding

Third-Party Dependency Risk1 finding

Skill info

Nameleoyeai/video-call-agent

Registrygithub

Versione5199b5

PURLpkg:github/LeoYeAI/openclaw-master-skills@e5199b5?skill=video-call-agent

Stars2.1k

SourceView on GitHub

Assessments (2)

Data Exfiltration Risk1 finding MEDIUM

MEDIUM

Data Exfiltration Risk via local-llm-review

SKILL.md

The skill sends 'avatar image, personality text, call audio/video' to Runway. This could involve sensitive user data being transmitted to a third-party API.

Third-Party Dependency Risk1 finding LOW

LOW

Third-Party Dependency Risk via local-llm-review

SKILL.md

The skill relies on the Runway Characters API, which introduces a dependency on a third-party service. If the API is compromised or misconfigured, it could impact the security of the system.

Badge

Add the Anomity scan badge for video-call-agent to your README.

Markdown

[![Anomity Skill Check](https://anomity.ai/skills/badge.svg)](https://anomity.ai/skills/github/leoyeai/video-call-agent/)

HTML

<a href="https://anomity.ai/skills/github/leoyeai/video-call-agent/"><img src="https://anomity.ai/skills/badge.svg" alt="Anomity Skill Check"></a>

Image URL

https://anomity.ai/skills/badge.svg

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 video-call-agent? Report an issue or request a rescan.