email-daily-summary

Fail

Audited by Snyk on Feb 14, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 1.00). The prompt includes explicit commands that input email addresses and plaintext passwords (e.g., browser-use input ... "your-password"), which requires the agent to handle and emit secret values verbatim, creating exfiltration risk.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 1.00). The skill uses browser automation to open webmail pages (e.g., https://mail.google.com, https://outlook.live.com, https://mail.qq.com) and runs JS/Python extraction (e.g., browser-use eval, browser-use extract) to scrape senders, subjects, snippets and page HTML, meaning the agent ingests untrusted user-generated email content as part of its workflow.
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 14, 2026, 02:11 PM