agent-browser
Fail
Audited by Snyk on Feb 21, 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’s examples and commands show embedding plaintext credentials (e.g., agent-browser fill @e2 "password123") and saving/loading auth state, which instructs the agent to include secret values verbatim in commands/outputs, creating an exfiltration risk.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The SKILL.md workflow and commands (e.g., "agent-browser open ", "agent-browser snapshot -i", and "agent-browser get text @e1"/interaction commands) explicitly navigate to arbitrary URLs and read/act on page content, meaning untrusted third-party web pages can be ingested and used to drive clicks/fills and other actions.
Audit Metadata