agent-browser-3

Fail

Audited by Snyk on Mar 4, 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 command examples that embed credentials verbatim (e.g., proxy URLs with user:pass, "set credentials user pass", example fills with a password, --headers with keys, cookies set name value), so an agent using it may be required to output secrets directly.

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

  • Third-party content exposure detected (high risk: 0.90). This skill explicitly navigates to arbitrary external URLs (agent-browser open in SKILL.md) and its templates (e.g., templates/capture-workflow.sh) snapshot and extract page text (agent-browser snapshot -i, agent-browser get text body), meaning the agent ingests untrusted public web content that can influence subsequent actions.
Audit Metadata
Risk Level
HIGH
Analyzed
Mar 4, 2026, 02:23 AM