agent-browser

Fail

Audited by Snyk on Feb 26, 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 examples and commands that embed credentials directly (e.g., fill "password123", set credentials , cookies set , set headers ) which require the agent to place secret values verbatim into generated commands/outputs.

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

  • Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to navigate to arbitrary URLs and to snapshot/get text/eval page content (e.g., "agent-browser open ", "agent-browser snapshot -i", "agent-browser get text body"), so the agent fetches and reads untrusted public web pages whose content can directly drive interactions and next actions.
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 26, 2026, 11:07 AM