Billionverify Skill

• Analyzed: May 11, 2026, 5:02 AM
• Findings: 1
• Version: 0.1.0
• Hash: a42caeaf6773f55750384aee32dd303109b423ac6281871b60d3028adf5cc60f
• Source: palm
• External report: View on VirusTotal

Findings (1)

The skill is suspicious due to exposing high-risk capabilities via the `Bash` tool, which can be exploited through prompt injection. Specifically, the `SKILL.md` defines `curl` commands that allow the AI agent to upload arbitrary local files (e.g., `file=@/path/to/emails.csv`), download files to arbitrary local paths (e.g., `-o results.csv`), and create webhooks pointing to arbitrary URLs (e.g., `"url": "https://your-app.com/webhooks/billionverify"`). While these are legitimate functionalities of the BillionVerify API, their exposure to an AI agent that processes user input creates significant vulnerabilities for data exfiltration, arbitrary file writes, or Server-Side Request Forgery (SSRF) if the agent is maliciously prompted.