antigravity
What this skill does
Automation of Antigravity desktop app via OpenCLI for message sending, conversation management, and code extraction.
github/jackwener - Command Injection Risk - 28k stars
Threat analysis
Skill info
pkg:github/jackwener/OpenCLI@a86d647?skill=antigravityAssessments (3)
Command Injection Risk
Command Injection Risk via local-llm-review
delete.js
The `delete.js` file allows deletion of Antigravity conversations with a `--yes` flag. If not properly secured, this could be exploited to delete user data without proper authorization.Exfiltration Risk
Exfiltration Risk via local-llm-review
serve.js
The `serve.js` file implements an HTTP server that acts as a proxy for the Anthropic Messages API, forwarding requests to a running Antigravity app via CDP. This could be used to exfiltrate data from Obfuscation Risk
Obfuscation Risk via local-llm-review
serve.js
The `generateMsgId` function in `serve.js` uses a custom character set for message ID generation, which could be used to obscure or obfuscate message identifiers, potentially hiding malicious activityBadge
Add the Anomity scan badge for antigravity 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 antigravity? Report an issue or request a rescan.
