agent-browser
Fail
Audited by Snyk on Mar 10, 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 instruct embedding credentials directly in commands (e.g., agent-browser fill @e2 "password123") and saving/loading auth state, which requires the agent to output secret values verbatim and thus poses 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's core workflow and commands in SKILL.md explicitly instruct the agent to open arbitrary URLs and snapshot pages (e.g., "agent-browser open " and "agent-browser snapshot -i"), meaning it fetches and ingests untrusted public web content that can influence subsequent interactions.
Audit Metadata