agent-browser
Fail
Audited by Snyk on Feb 22, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 0.90). The prompt includes commands that embed plaintext secrets (e.g., fill @e2 "password123", set credentials user pass, set headers '{"X-Key":"v"}' and saving/loading auth.json), so an agent following it would likely need 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: 1.00). This skill explicitly browses arbitrary URLs via commands like "agent-browser open " and ingests page content with "agent-browser snapshot", "get text/html", and "eval" (in SKILL.md core workflow and commands), meaning untrusted third-party web content can be read and acted on and thus could inject instructions.
Audit Metadata