Agent Browser

Fail

Audited by Snyk on Mar 9, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 0.90). The prompt includes commands that embed plaintext secrets (e.g., fill @e2 "password123", set credentials user pass, set headers '{"X-Key":"v"}' and saving/loading auth.json), so an agent following it would likely need to output 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). This skill (SKILL.md) instructs the agent to open arbitrary URLs via "agent-browser open " and to snapshot, get text/html, eval JavaScript, and interact with page elements (e.g., "agent-browser snapshot -i", "agent-browser get html @e1", "agent-browser eval ..."), which clearly ingests and acts on untrusted public web content that can influence subsequent actions.
Audit Metadata
Risk Level
HIGH
Analyzed
Mar 9, 2026, 08:18 PM