agent-browser

Fail

Audited by Snyk on Mar 5, 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 that place plaintext credentials directly into commands (e.g., agent-browser fill @e2 "password123") which encourages the agent 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: 0.90). The SKILL.md core workflow explicitly lets the agent navigate to arbitrary public URLs via "agent-browser open " and then snapshot/get text/eval page content (e.g., "agent-browser snapshot -i", "agent-browser get text @e1", "agent-browser eval"), meaning untrusted third-party webpages can be read and used to drive subsequent clicks/interactions and decisions.
Audit Metadata
Risk Level
HIGH
Analyzed
Mar 5, 2026, 08:42 AM