NYC

agent-browser

Fail

Audited by Snyk on Feb 16, 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 workflows that embed credentials directly into CLI commands (e.g., agent-browser fill @e2 "password123" and fill with "$PASSWORD"), which require the agent to output secret values verbatim and therefore pose an exfiltration risk.

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

  • Third-party content exposure detected (high risk: 0.90). agent-browser explicitly opens arbitrary public URLs (agent-browser open ), snapshots and extracts page content (agent-browser snapshot -i, agent-browser get text body, --json), so the agent will ingest untrusted, user-generated content from the open web.
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 16, 2026, 12:52 AM